CN109191940A - A kind of exchange method and smart machine based on smart machine - Google Patents
A kind of exchange method and smart machine based on smart machine Download PDFInfo
- Publication number
- CN109191940A CN109191940A CN201811015615.6A CN201811015615A CN109191940A CN 109191940 A CN109191940 A CN 109191940A CN 201811015615 A CN201811015615 A CN 201811015615A CN 109191940 A CN109191940 A CN 109191940A
- Authority
- CN
- China
- Prior art keywords
- smart machine
- projection
- module
- question
- image
- 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
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/065—Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/067—Combinations of audio and projected visual presentation, e.g. film, slides
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention provides a kind of exchange method and smart machine based on smart machine, when user meets difficulty, asked questions content can be directed toward, answer content is inquired to smart machine, when smart machine is identified in the voice messaging of user containing keyword is putd question to, the smart machine is obtained by photographing module and puts question to area image；Then subject of question is parsed from the enquirement area image that the photographing module obtains, and obtains the corresponding answer content of the subject of question；Projection information is generated further according to the answer content, and the projection information is projected to by default view field according to the projection pattern that user selects.The present invention is integrated with acquisition problem on intelligent devices, answers a question, shows the functions such as answer content, it can be when student encounters difficulty of learning, obtain the asked a question content of student, and answer content is shown in a manner of projecting, while providing learning assistance for student, the burden of parent is decreased.
Description
Technical field
The present invention relates to intelligence learning product scope, espespecially a kind of exchange method and smart machine based on smart machine.
Background technique
Under current environment, the learning pressure of China student is generally bigger, has operation in heaps to need to complete daily.It learns
Life can encounter various problem, such as new word will not be read, counting will not do, in this case when fulfiling assignment often
It needs to be taught in time.But many parents can not teach child to complete homework at all, cause very for fear of operating pressure
More child's school grade declines.
With the development of science and technology, occur electronic equipment, such as mobile phone, tablet computer, study plate etc. on the market,
Student is helped to solve the problems, such as to encounter in operation.A kind of mode is after shooting photo against books using electronic equipment, to search out
The answer of problem；Another way is to say problem against electronic equipment, searches for the answer gone wrong.
The above mode for helping student to solve shop problem has the following deficiencies: that (one) is detached from the working scene of student,
It is inquired and is checked on additional smart machine；(2) smart machines such as mobile phone, tablet computer are not detached from, students' union is to make
Industry is to play mobile phone or tablet computer by taking this opportunity, and delays study；(3) when saying problem against electronic equipment, if student's expression is not
Clear problem can not then help student to solve shop problem.
The present invention timely helps to provide when student encounters difficulty of learning, completes when student being allowed to meet difficulty autonomous
Study, thus provide a kind of exchange method and smart machine based on smart machine.
Summary of the invention
The object of the present invention is to provide a kind of exchange method and smart machine based on smart machine, can encounter in student
It provides when practising difficult and timely helps.
Technical solution provided by the invention is as follows:
The present invention provides a kind of exchange methods based on smart machine, comprising:
When smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine passes through camera shooting
Module, which obtains, puts question to area image；
The smart machine parses subject of question from the enquirement area image that the photographing module obtains, and obtains
Take the corresponding answer content of the subject of question；
The smart machine generates projection information according to the answer content, and according to the projection pattern of user's selection by institute
It states projection information and is projected to default view field.
This programme combines necessity --- lamps and lanterns used when student's study, and acquisition problem, solution are integrated on lamps and lanterns
The functions such as question and answer topic, display answer content can provide help in time when student's study is met difficulty for student.This programme
In, after smart machine gets answer content, the mode that can be projected is cast out content is answered, and does not need external display
Screen adds display screen on lamps and lanterns, improves the popularity of smart machine application.
Preferably, when smart machine listens in the voice messaging of user containing keyword is putd question to, the smart machine
It is obtained by photographing module and puts question to area image, the voice messaging of smart machine monitoring users is further comprised the steps of: before this step,
And it whether detects in the voice messaging containing enquirement keyword；
If the smart machine detects to continue the language of monitoring users without containing keyword is putd question in the voice messaging
Message breath；If the smart machine detects to open photographing module containing the enquirement keyword in the voice messaging.
In the present solution, " how this problem does " or " how the 5th topic is done " can be putd question to when student meets difficulty, intelligently set
After in analyzing voice containing keyword is putd question to, i.e., openable photographing module, which obtains, puts question to area image.This programme is not
Photographing module is opened in real time, but just opens photographing module under certain conditions, reduces the energy consumption of photographing module.
Preferably, when smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine
It is obtained by photographing module and puts question to area image, this step specifically includes:
When smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine opens camera shooting
Module obtains the interface image of books using the edge for detecting books as boundary；
The smart machine detects that target is directed toward region from the interface image of the books, and the target is directed toward
The corresponding image in region is as the enquirement area image.
This programme obtains the interface image of books first, then obtains in interface image when obtaining enquirement area image
It takes target to be directed toward region as area image is putd question to, can will test in range shorter to the interface of books, reduce detection
Interference.
Preferably, the projection information is projected to by default view field with the projection pattern that user selects, this step tool
Body includes:
When user selects the projection pattern to project for LED, the smart machine is by projection module with the projection side LED
The projection information is projected to default view field by formula；
Or when user selects the projection pattern as light projection, the smart machine is thrown by projection module with light
It penetrates mode and the projection information is projected to default view field；
Or when user selects the projection pattern to project for 3D holography, the smart machine is complete with 3D by projection module
It ceases mode of delivery and the projection information is projected to default view field；
Or when user selects the projection pattern to project for AR, the smart machine is by projection module with the projection side AR
The projection information is projected to default view field by formula.
A variety of mode of delivery are provided in this programme, can satisfy different projection demands, such as the answer content of projection
Comprising three-dimensional image or when chemical experiment image, that is, 3D holography mode of delivery can be used to be projected, when the solution of projection
It answers in content containing there are many kinds of when color, that is, LED mode of delivery can be used, so that the color differentiation of projection is more obvious.
Preferably, it further comprises the steps of:
The smart machine record described problem content, which is formed, puts question to record, and puts question in record in history and search whether to deposit
Record is approximately being putd question to described problem content；
If being putd question in record in history and there is enquirement similar with described problem content record, by the similar enquirement
It records corresponding subject of question and answer content is projected to the default view field.
In the present solution, the problem of student asks can all be recorded by smart machine, formed and put question to record, proposes phase when next time
As problem when can project Similar Problems and answer content, the problem of not understanding before allowing student to look back, intensification are known same
The study for knowing point, consolidates knowledge point.
The present invention also provides a kind of smart machines, comprising:
Photographing module, for when smart machine identifies in the voice messaging of user containing keyword is putd question to, acquisition to be mentioned
Ask area image；
Parsing module is electrically connected with the photographing module, the enquirement administrative division map for obtaining from the photographing module
Subject of question is parsed as in；
Answer obtains module, is electrically connected with the parsing module, for obtaining the corresponding answer content of the subject of question；
Projection information generation module obtains module with the answer and is electrically connected, throws for being generated according to the answer content
Shadow information；
Projection module is electrically connected with the projection information generation module, and the projection pattern for being selected according to user is by institute
It states projection information and is projected to default view field.
Photographing module, parsing module, answer acquisition module, projection information are provided on the smart machine provided in this programme
Generation module and projection module realize acquisition problem, answer a question, show the functions such as answer content, encounter in student's study
When difficult, help can be provided for student in time.In the present solution, after smart machine gets answer content, with the side of projection
Formula is cast out content is answered, and is not needed externally connected with display screen curtain or is added display screen on lamps and lanterns, increases the wide of application
General property.
Preferably, the smart machine further include:
Whether speech detection module for the voice messaging of monitoring users, and detects in the voice messaging containing enquirement
Keyword；
The speech detection module detects to close in the voice messaging without containing enquirement if being also used to the smart machine
Keyword then continues the voice messaging of monitoring users；
Control module is electrically connected with the speech detection module, is closed in the voice messaging containing enquirement out for identification
When keyword, photographing module is opened.
In the present solution, " how this problem does " or " how the 5th topic is done " can be putd question to when student meets difficulty, intelligently set
After in analyzing voice containing keyword is putd question to, i.e., openable photographing module, which obtains, puts question to area image.This programme is not
Photographing module is opened in real time, but just opens photographing module under certain conditions, reduces the energy consumption of photographing module.
Preferably, the intelligent terminal includes:
Control module, for being electrically connected with the speech detection module, for identifying use when the speech detection module
When in the voice messaging at family containing keyword is putd question to, photographing module is opened；
The photographing module is also electrically connected with the control module, for obtaining using the edge of the books detected as boundary
The interface image of books；
Region identification module is putd question to, is electrically connected with the photographing module, for being detected from the interface image of the books
Target is directed toward region out, and the target is directed toward the corresponding image in region as the enquirement area image.
This programme obtains the interface image of books first, then obtains in interface image when obtaining enquirement area image
It takes target to be directed toward region as area image is putd question to, can will test in range shorter to the interface of books, reduce detection
Interference.
Preferably, the projection module, for when user selects the projection pattern to project for LED, the intelligence to be set
It is standby that the projection information is projected to LED mode of delivery by default view field by projection module；
Or for when user select the projection pattern as light projection, the smart machine to pass through projection module with lamp
The projection information is projected to default view field by light projection mode；
Or for when user select the projection pattern be 3D holography project when, the smart machine pass through projection module with
The projection information is projected to default view field by 3D holography mode of delivery；
Or for when user selects the projection pattern to project for AR, the smart machine to be thrown by projection module with AR
It penetrates mode and the projection information is projected to default view field.
A variety of mode of delivery are provided in this programme, can satisfy different projection demands, such as the answer content of projection
Comprising three-dimensional image or when chemical experiment image, that is, 3D holography mode of delivery can be used to be projected, when the solution of projection
It answers in content containing there are many kinds of when color, that is, LED mode of delivery can be used, so that the color differentiation of projection is more obvious.
Preferably, the smart machine further include:
Logging modle forms enquirement record for recording described problem content；
Searching module is electrically connected with the logging modle, for history put question to record in search whether exist with it is described
Problem content approximately puts question to record；
The projection module is electrically connected with the searching module, if be also used to history put question to record in exist with it is described
The similar enquirement record of problem content, then record corresponding subject of question for the similar enquirement and answer content be projected to
The default view field.
In the present solution, the problem of student asks can all be recorded by smart machine, formed and put question to record, proposes phase when next time
As problem when can project Similar Problems and answer content, the problem of not understanding before allowing student to look back, intensification are known same
The study for knowing point, consolidates knowledge point.
Preferably, or；The smart machine includes intelligent desk lamp, and the photographing module and the projection module are arranged in institute
State the head of intelligent desk lamp, and the projecting direction of the camera shooting direction of the photographing module and the projection module is towards the intelligence
The pedestal side of energy desk lamp；Or；The smart machine includes intelligent wall lamp, and the photographing module and projection module setting exist
On the intelligence wall lamp, and the projecting direction of the camera shooting direction of the photographing module and the projection module is preset towards described
View field side；Or；The smart machine includes intelligent pendent lamp, and the photographing module and the projection module are arranged described
On intelligent pendent lamp, and the camera shooting direction of the photographing module and the projecting direction of the projection module are towards the default projection
Region side.
A kind of exchange method and smart machine based on smart machine provided through the invention, can bring it is following at least
It is a kind of the utility model has the advantages that
The present invention is integrated on intelligent devices in order to be capable of providing and timely help when student encounters difficulty of learning
Acquisition problem answers a question, shows the functions such as answer content, when student's study is met difficulty, need to only point to the problem of being ignorant of
Say: " how this problem does ", smart machine can acquire enquirement area image, then by image analysis technology acquisition problem
Hold, then answer content is obtained by knowledge base, the content of answer is cast out, learns to refer to for student.It can be seen that smart machine
It has served as and has taught a duty, while providing learning assistance for student, decreased the burden of parent.
Detailed description of the invention
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, to a kind of based on smart machine
Above-mentioned characteristic, technical characteristic, advantage and its implementation of exchange method and smart machine are further described.
Fig. 1 is a kind of flow chart of one embodiment of the exchange method based on smart machine of the present invention；
Fig. 2 is a kind of flow chart of another embodiment of the exchange method based on smart machine of the present invention；
Fig. 3 is a kind of flow chart of another embodiment of the exchange method based on smart machine of the present invention；
Fig. 4 is a kind of structural schematic diagram of one embodiment of smart machine of the present invention；
Fig. 5 is a kind of structural schematic diagram of another embodiment of smart machine of the present invention；
Fig. 6 is a kind of structural schematic diagram of smart machine.
Drawing reference numeral explanation:
1- photographing module, 2- parsing module, 3- answer obtain module, 4- projection information generation module, 5- projection module, 6-
Speech detection module, 7- control module, 8- logging modle, 9- searching module, 10- put question to region identification module.
Specific embodiment
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, Detailed description of the invention will be compareed below
A specific embodiment of the invention.It should be evident that drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing, and obtain other embodiments.
To make simplified form, part related to the present invention is only schematically shown in each figure, they are not represented
Its practical structures as product.In addition, there is identical structure or function in some figures so that simplified form is easy to understand
Component only symbolically depicts one of those, or has only marked one of those.Herein, "one" is not only indicated
" only this ", can also indicate the situation of " more than one ".
The present invention provides a kind of one embodiment of exchange method based on smart machine, as shown in Figure 1, comprising:
For S1 when smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine is by taking the photograph
Area image is putd question to as module obtains；
Photographing module in the present invention can be camera, it is mountable on intelligent devices, smart machine includes intelligent station
Lamp, intelligent pendent lamp, intelligent wall lamp etc., it is mountable near desk, enable smart machine by installing taking the photograph on the body
As module gets the image information of books on desk.
Student do not know or the topic that will not do in study if having to encounter, can be with finger to no topic, then
It says that " how this problem does " or " how the first topic is done " etc. are similar and puts question to language.Smart machine can acquire the voice letter of user in real time
Breath asks voice messaging conversion to text information, then judges whether there is and put question to keyword (such as " how doing ", " how doing ", " such as
What is said " etc.), when smart machine identifies in the voice messaging of user containing keyword is putd question to, camera can be analyzed and collected
Image, the direction of profile and finger sold by image recognition technology identification, and be directed toward on region and find out in finger
User wants the region where the topic of inquiry, using the image in this region as enquirement area image.
Smart machine described in S2 parses subject of question from the enquirement area image that the photographing module obtains, and
Obtain the corresponding answer content of the subject of question；
Specifically, can be integrated in smart machine picture processing chip (such as FH8510 picture processing chip or
FMS6502 picture processing chip), the subject of question putd question in area image can be parsed to puing question to area image to identify,
Such as parse enquirement area image, obtain subject of question: " the 4th topic, Xiao Ming have bought 5 jin of apples, 3 yuan of apple per jin, little Ming Yi
Need that how much is paid altogether? ".Smart machine can find out subject of question pair in the knowledge base stored in advance according to subject of question
The answer content (including topic parsing, detailed answer step etc.) answered.
Smart machine described in S3 generates projection information according to the answer content, and will according to the projection pattern of user's selection
The projection information is projected to default view field.
Specifically, projection module, such as Miniature projector can be equipped on smart machine.Smart machine can be according to preset throwing
Shadow template (including: answer column, parsing column, knowledge point column), is added to projective module for content corresponding in answer content
In each column of plate, to generate projection information.User can preset projection module projection pattern (including LED projection,
Light projection, 3D holography projection, AR projection), it is projected to projection module by projection information according to the projection pattern of selection default
View field.
When projection, a desktop area can be detected from the image information that photographing module acquires by image recognition technology,
Using this region as default view field.In order to generate better drop shadow effect in projection, it mating can also increase by one piece of throwing
Projection plate can be placed on desk, camera can automatically identify throwing by image recognition technology by shadow plate, student in study
The position of plate is penetrated, while adjusting the projecting direction of projection module, image is projected on projection plate.
An also settable sight line detector on the smart machine, sight line detector acquire the head image of user,
And the direction of visual lines of user is detected according to the head image, default view field is then determined on the direction of visual lines；
Or；The eye image of sight line detector acquisition user on the smart machine, and detect to use according to the eye image
Then the direction of visual lines at family determines default view field on the direction of visual lines；
Specifically, checking the 3-D image projected in order to facilitate user, it can be detected and be used by a sight line detector
The direction of visual lines at family.The example of two kinds of detection user's direction of visual lines is provided in the present embodiment:
1, it can be detected on face by the head image that sight line detector obtains human body by face recognition technology
Each characteristic point (such as nose, eyes, cheekbone, eyebrow, mouth characteristic point) and these characteristic points are in world's three-dimensional system of coordinate
Under coordinate, using eyes formed rectilinear direction as X-coordinate axis direction, between eyes midpoint and nose formation straight line side
To for Y coordinate axis direction, the eyes of default user are head-up front, then with X-coordinate axle and Y-coordinate axle mutually orthogonal direction,
Straight line where can be identified as direction of visual lines.Then direction of visual lines is confirmed with face orientation again.
It 2, can include shooting unit by sight line detector, for shooting the eye image of user and obtaining its zoom
Value, the shooting unit have zoom function；Cornea determination unit, distinguishes cornea image from eye image；Basic point is specified single
Member, based on the cornea image come the eyeball center of designated user, and will be in object and hanging down from eyeball center to object
Intersection point between line is appointed as basic point；Distance measuring unit specifies the zoom value of the predefined size of the image of instruction cornea, and
And based on the zoom value come the specified distance from cornea to object；Sight amount of movement designating unit, the shifting based on cornea image
Momentum specifies the amount of movement of cornea, and is specified on object based on the amount of movement of cornea and the distance from cornea to object
Sight amount of movement；And focus designating unit, focus is specified based on datum mark and sight amount of movement, so that it is determined that
The direction of visual lines of user out.Sight line detector on smart machine can detecte the direction of visual lines of user, to make to determine
Default view field just in the fixation range of user, allow user can be to intuitively understanding very much answer content.
This programme combines necessity --- lamps and lanterns used when student's study, and acquisition problem, solution are integrated on lamps and lanterns
The functions such as question and answer topic, display answer content can provide help in time when student's study is met difficulty for student.This programme
In, after smart machine gets answer content, answer content is cast out in a manner of projection, does not need externally connected with display screen
Curtain adds display screen on lamps and lanterns, increases the popularity of application.
As shown in Fig. 2, the present invention also provides a kind of another embodiments of exchange method based on smart machine, including
Step:
The voice messaging of S01 smart machine monitoring users, and whether detect in the voice messaging containing enquirement keyword；
When student encounters problems during learning or inscribing, can then be said: " this with finger to the topic being ignorant of
How problem does " or " first topic how to do " etc. is similar puts question to language.Speech detection module in smart machine includes microphone, can
The voice messaging for obtaining user, after getting the voice messaging of user, speech detection module converts the voice messaging of user
For text information；Then judge in text information whether containing keyword is putd question to (such as the keys such as " how doing ", " how doing "
Word).
If the S02 smart machine detects to continue monitoring users without containing keyword is putd question in the voice messaging
Voice messaging；
If the S03 smart machine detects to open camera shooting mould containing the enquirement keyword in the voice messaging
Block；
When smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine passes through S11
Photographing module obtains the interface image of books using the edge for detecting books as boundary；
Specifically, in order to preferably identify the books on desktop books identification model can be trained, the present embodiment is with training
For Unet parted pattern.It will be based on tensorflow deep learning frame, building Unet divides network.In order to reduce segmentation net
The size of network promotes the efficiency of segmentation network, modifies existing lightweight mobilenet_v2 network structure, be used for unet
Network code part, unet decoded portion use simple convolutional neural networks.
A variety of single desktop pictures and a variety of single book images can be acquired before training, by each Zhang Danyi desk-top picture
Picture and each Zhang Danyi book image carry out multiple combinations and (such as are placed in single book image on single book image not
Same position), the combination image of several single book images and single desktop picture is obtained, then by several combination images with 4:1
Be divided into training set and verifying collection, by training set by Unet divide network be trained, when Unet segmentation network training set with
When IOU (gauge of segmentation network) value on test set is both greater than 0.95, Unet parted pattern is obtained.
After camera obtains desktop picture, binary segmentation is carried out to desktop picture by Unet parted pattern, obtains table
The binary segmentation figure of face image, and the edge of books is extracted from the binary segmentation figure of desktop picture, so that it is determined that books out
Position, the interface image of books is got from desktop picture.
In this programme and non real-time unlatching photographing module, but photographing module is just opened under certain conditions, reduce
The energy consumption of photographing module.
Smart machine described in S12 detects that target is directed toward region from the interface image of the books, and by the target
The corresponding image in region is directed toward as the enquirement area image.
Smart machine can be identified from interface image after getting the interface image of books by image recognition technology
The finger of user out, and region pointed by finger tip is defined as target and is directed toward region, then target is directed toward to the image in region
As enquirement area image.
Smart machine described in S2 parses subject of question from the enquirement area image that the photographing module obtains, and
Obtain the corresponding answer content of the subject of question；
In the present embodiment, smart machine can send subject of question after parsing subject of question in enquirement area image
To server.Knowledge base can be stored in advance in server end, and server can be searched corresponding according to subject of question in knowledge base
Answer content, and will answer content return to smart machine.Storage knowledge base is not needed in the technical program, on smart machine
Related data, the requirement to smart machine reservoir is reduced, to reduce the manufacturing cost of smart machine.
Smart machine described in S3 generates projection information according to the answer content, and will according to the projection pattern of user's selection
The projection information is projected to default view field.
Projection module, such as Miniature projector can be equipped on smart machine.Smart machine can be according to preset projection template
(including: answer column, parsing column, knowledge point column) will answer corresponding content in content and be added to each of projection template
In a column, to generate projection information.User can preset projection module projection pattern (including LED projection, light throw
Penetrate, 3D holography projection, AR projection), projection information is projected to default view field.
Preferably, in the present embodiment, the smart machine can be analyzed according to the subject of question and obtain the subject of question
Affiliated subject type；And the subject type according to belonging to the subject of question, select corresponding projection pattern will be in the answer
Appearance is projected to the default view field.
Specifically, intelligent terminal can carry out semantic understanding to subject of question, subject belonging to the subject of question is analyzed
Type；The matching of subject can also be carried out by the subject keyword in subject of question, for example, if when occurring chemical formula in topic,
It can determine whether out that subject of question is chemical classes, if occur a large amount of English in topic, can determine whether out that subject of question is English classification；
Again alternatively, the page where the page number or subject of question of page where the question number of subject of question perhaps subject of question can also be passed through
Position, match corresponding books, then the subject category according to this books, determine the subject class of subject of question
Not.
In order to make the mode of projection be more in line with the characteristic of the affiliated subject of subject of question, can be automatically selected in projection corresponding
Projection pattern projected.
For example, since English is all character type answer, being thrown with plane when the subject belonging to the subject of question is English
The mode of shadow, which carries out projection, can reach better viewing effect；And the subject belonging to the subject of question is when being geometry, due to
Geometric figure is solid figure, if being projected in a manner of plane projection, can understand student that answer causes certain difficulty,
The purpose for providing and solving a problem for student is provided；And projected in a manner of tripleplane, student can be from different perspectives to projection
Three-dimensional geometric shapes out are understood, the problem of encountering is made to be more easier to answer.
For another example when the affiliated subject of subject of question is geographical, due to being all much geographically about mountainous region, ocean, gas
The research such as time possibly can not allow student to have intuitive experience if projecting answer content in a manner of plane projection.As student exists
When understanding the landform such as karst landform, "Danxia" landform, coastal landform, glacial landforms, if projecting correlation in a manner of plane projection
Picture, student may the characteristic of all kinds of topography and geomorphologies can not be understood completely, thus be not easy distinguish different terrain landforms, and
Answer content is projected in a manner of tripleplane, student can from different angles observe various landforms, it is easier to area
Divide the feature of different terrain landforms.
As shown in figure 3, the present invention provides a kind of one embodiment of exchange method based on smart machine, comprising:
The voice messaging of S01 smart machine monitoring users, and whether detect in the voice messaging containing enquirement keyword；
If the S02 smart machine detects to continue monitoring users without containing keyword is putd question in the voice messaging
Voice messaging；
If the S03 smart machine detects to open camera shooting mould containing the enquirement keyword in the voice messaging
Block；
S11 when smart machine identifies in the voice messaging of user containing keyword is putd question to, open by the smart machine
Photographing module obtains the interface image of books using the edge for detecting books as boundary；
Smart machine described in S12 detects that target is directed toward region from the interface image of the books, and by the target
The corresponding image in region is directed toward as the enquirement area image.
Smart machine described in S2 parses subject of question from the enquirement area image that the photographing module obtains, and
Obtain the corresponding answer content of the subject of question；
Smart machine described in S3 generates projection information according to the answer content, and will according to the projection pattern of user's selection
The projection information is projected to default view field, optionally, described when user selects the projection pattern to project for LED
The projection information is projected to default view field with LED mode of delivery by projection module by smart machine；Or when user selects
Select the projection pattern be light projection when, the smart machine by projection module in a manner of light projection by the projection letter
Breath is projected to default view field；Or when user selects the projection pattern to project for 3D holography, the smart machine passes through
The projection information is projected to default view field with 3D holography mode of delivery by projection module；Or when user selects the projection
When mode is that AR is projected, the projection information is projected to default throwing with AR mode of delivery by projection module by the smart machine
Shadow zone domain.
A variety of mode of delivery are provided in the present embodiment for user's selection, can meet the projection need of different projection contents
It asks.
Smart machine described in S41 records the formation of described problem content and puts question to record, and lookup is in history enquirement record
No presence approximately puts question to record with described problem content；
If S42 is putd question in record in history has enquirement similar with described problem content record, will be described similar
Enquirement records corresponding subject of question and answer content is projected to the default view field.
It is recorded specifically, smart machine can ask a question user, is formed and put question to record, inquired again when user is subsequent
It, can be by close problem and answer content push to user when similar problem.Such as content is when user's what is heard the problem of
" next sentence of ' one hundred days near the mountain to the greatest extent ' is _ _ _ _ ", and user also asked " upper one of ' attaining a yet higher goal ' is _ _ _ _ " in the past, that
, smart machine to user project answer information after, can by it is similar enquirement record corresponding subject of question and answer in
Appearance all projects default view field, deepens cognition of the user to similar knowledge point.
Optionally, in the present embodiment, the smart machine analyzes the subject of question, obtains belonging to the subject of question
Subject, the specific chapters and sections of the affiliated subject of subject of question and the concrete knowledge point of the affiliated chapters and sections of the subject of question, and remember
It records history of forming and puts question to record；The smart machine puts question to record according to the history in preset period of time, generates different subjects
It practises in the learning evaluation report of different chapters and sections in appraisal report and/or each subject and/or each chapters and sections of each subject not
Learning evaluation with knowledge point is reported.
For user after inquiry problem, smart machine can all record relevant subject of question, and carry out to subject of question
Analysis, obtains subject belonging to the subject of question, in the specific chapters and sections of the affiliated subject of subject of question and the enquirement
The concrete knowledge point of chapters and sections belonging to holding.When user wants to know about the study situation of nearest a period of time, smart machine can root
Record is putd question to according to the history of this period, corresponding learning evaluation report is generated, user is helped to understand current study condition.Example
When needing the learning evaluation of this subject of this term mathematics to report such as user, then it can be putd question to and be recorded according to history, smart machine meeting
The historical record that this term is asked questions extracts, and is sorted out according to the affiliated chapters and sections of each problem, and affiliated knowledge point is returned
Class, evaluate user in Mathematics Discipline each chapters and sections, each knowledge point study situation.
In addition, the present embodiment considers student when needing to project the stereo-pictures such as geometric figure or kinds of experiments equipment
Can often there are mapping, even auxiliary line, the operation such as add other figures when doing geometry topic, when doing experimental problem, it is often necessary to will
A variety of equipment are combined, while student is more complete, comprehensively checks the geometric figure being projected out in order to make, energy when testing
Enough there is more intuitive experience, this programme increases edit operation when being projected in a manner of tripleplane, and user can be
It is edited accordingly on the 3-D image projected, learning Content is best understood from this.
For example, when the time for touching arbitrary point on the 3-D image reaching the first preset time, or work as described in touching
On 3-D image at any at least 3, it is image drag operation that the smart machine, which parses the edit operation, and according to
The image drag operation at family drags 3-D image；
When the time for touching arbitrary point on the 3-D image reaching the second preset time, the smart machine parses institute
Edit operation is stated as image rotation operation, and 3-D image is rotated according to the operation of the image rotation of user.
When any two points on the touching 3-D image, and when two touch points distance diminutions, the smart machine solution
The edit operation is analysed as image down operation；When touching any two points on the 3-D image, and two touch points distances
When becoming larger, the smart machine parses the edit operation as image amplifying operation；
Reach the 4th preset time when the time for touching any point on the 3-D image, and touch points moving distance is big
When pre-determined distance, it is to make graphic operation that the smart machine, which parses the edit operation,；
When user clutches a certain figure in the 3-D image, the smart machine parses the editor behaviour
It is operated as image-erasing；And add when the speech detection module 6 of smart machine listens in the voice messaging of user comprising figure
When adding information, then the corresponding figure of the figure addition information is added in 3-D image, such as user says " addition cylindrical body ",
Smart machine can analyze by semantic understanding when listening to the words and need to add " cylindrical body " this figure.
As shown in figure 4, smart machine includes photographing module 1, solution the present invention also provides a kind of embodiment of smart machine
Analyse module 2, answer obtains module 3, projection information generation module 4, projection module 5:
Photographing module 1, for when smart machine identifies in the voice messaging of user containing keyword is putd question to, acquisition to be mentioned
Ask area image；
Parsing module 2 is electrically connected with the photographing module 1, for from the enquirement region that the photographing module 1 obtains
Subject of question is parsed in image；
Answer obtains module 3, is electrically connected with the parsing module 2, for obtaining in the corresponding answer of the subject of question
Hold；
Projection information generation module 4 obtains module 3 with the answer and is electrically connected, for being generated according to the answer content
Projection information；
Projection module 5 is electrically connected with the projection information generation module 4, and the projection pattern for being selected according to user will
The projection information is projected to default view field.
Specifically, photographing module 1 in the present invention can be camera, it is mountable on intelligent devices, smart machine packet
Intelligent desk lamp, intelligent pendent lamp, intelligent wall lamp etc. are included, it is mountable near desk, enable smart machine by being mounted on this
Photographing module 1 on body gets the image information of books on desk.
Student in study, if having encounter do not know or will not do topic when, no topic can be directed toward with finger,
Then it says that " how this problem does " or " how the first topic is done " etc. are similar and puts question to language.Smart machine can acquire the voice of user in real time
Information asks voice messaging conversion to text information, then judge whether to have enquirement keyword in text information (such as " how doing ",
" how doing ", " how saying " etc.), when smart machine identifies in the voice messaging of user containing keyword is putd question to, can analyze
Camera acquired image is directed toward by the direction of profile and finger that image recognition technology identification is sold, and in finger
The region where the topic of the desired inquiry of user is found out on region, and using the image in this region as enquirement area image.
Picture processing chip (such as FH8510 picture processing chip or FMS6502 image can be integrated in smart machine
Handle chip), the subject of question in image-text area image can be parsed, such as parsing is putd question to puing question to area image to identify
Area image obtains subject of question: " the 4th topic, Xiao Ming have bought 5 jin of apples, 3 yuan of apple per jin, and Xiao Ming needs to pay altogether more
Few money? ".Smart machine can be found out in the corresponding answer of subject of question according to subject of question in the knowledge base stored in advance
Hold (including topic parsing, detailed answer step etc.).
Smart machine can will be solved according to preset projection template (including: answer column, parsing column, knowledge point column)
It answers corresponding content in content to be added in each column of projection template, to generate projection information.It can be set on smart machine
There are a projection module 5, such as Miniature projector, user can preset projection pattern (including the LED projection, light of projection module 5
Projection, 3D holography projection, AR projection), after smart machine, which will answer content, generates projection information, projection module 5 can be passed through
Projection information is projected to default view field.
When projection, a desktop area can be detected from the image information that photographing module 1 acquires by image recognition technology
Domain, using this region as default view field.In order to generate better drop shadow effect in projection, also mating one piece can be increased
Projection plate can be placed on desk, camera can be automatically identified by image recognition technology by projection plate, student in study
The position of plate is projected, while adjusting the projecting direction of projection module, image is projected on projection plate.
The image projected is checked in order to facilitate user, can by the way that a sight line detector is arranged on intelligent devices,
To detect the direction of visual lines of user, default view field is determined on the direction of visual lines of user.Specifically, the line-of-sight detection
Device acquires the head image of user, and the direction of visual lines of user is detected according to the head image, then in the sight
Default view field is determined on direction；The eye image of sight line detector acquisition user on the smart machine, and according to
The eye image detects the direction of visual lines of user, and default view field is then determined on the direction of visual lines.This implementation
The example of two kinds of detection user's direction of visual lines is provided in example:
1, it can be detected on face by the head image that sight line detector obtains human body by face recognition technology
Each characteristic point (such as nose, eyes, cheekbone, eyebrow, mouth characteristic point) and these characteristic points are in world's three-dimensional system of coordinate
Under coordinate, using eyes formed rectilinear direction as X-coordinate axis direction, between eyes midpoint and nose formation straight line side
To for Y coordinate axis direction, the eyes of default user are head-up front, then with X-coordinate axle and Y-coordinate axle mutually orthogonal direction,
Straight line where can be identified as direction of visual lines.Then direction of visual lines is confirmed with face orientation again.
It 2, can include shooting unit by sight line detector, for shooting the eye image of user and obtaining its zoom
Value, the shooting unit have zoom function；Cornea determination unit, distinguishes cornea image from eye image；Basic point is specified single
Member, based on the cornea image come the eyeball center of designated user, and will be in object and hanging down from eyeball center to object
Intersection point between line is appointed as basic point；Distance measuring unit specifies the zoom value of the predefined size of the image of instruction cornea, and
And based on the zoom value come the specified distance from cornea to object；Sight amount of movement designating unit, the shifting based on cornea image
Momentum specifies the amount of movement of cornea, and is specified on object based on the amount of movement of cornea and the distance from cornea to object
Sight amount of movement；And focus designating unit, focus is specified based on datum mark and sight amount of movement, so that it is determined that
The direction of visual lines of user out.
This programme combines necessity --- lamps and lanterns used when student's study, and acquisition problem, solution are integrated on lamps and lanterns
The functions such as question and answer topic, display answer content can provide help in time when student's study is met difficulty for student.This programme
In, after smart machine gets answer content, answer content is cast out in a manner of projection, does not need externally connected with display screen
Curtain adds display screen on lamps and lanterns, increases the popularity of application.
Preferably, in the present embodiment, the smart machine can be analyzed according to the subject of question and obtain the subject of question
Affiliated subject type；And the subject type according to belonging to the subject of question, select corresponding projection pattern will be in the answer
Appearance is projected to the default view field.
Specifically, intelligent terminal can carry out semantic understanding to subject of question, subject belonging to the subject of question is analyzed
Type；The matching of subject can also be carried out by the subject keyword in subject of question, for example, if when occurring chemical formula in topic,
It can determine whether out that subject of question is chemical classes, if occur a large amount of English in topic, can determine whether out that subject of question is English classification；
Again alternatively, the page where the page number or subject of question of page where the question number of subject of question perhaps subject of question can also be passed through
Position, match corresponding books, then the subject category according to this books, determine the subject class of subject of question
Not.
In order to make the mode of projection be more in line with the characteristic of the affiliated subject of subject of question, can be automatically selected in projection corresponding
Projection pattern projected.
For example, since English is all character type answer, being thrown with plane when the subject belonging to the subject of question is English
The mode of shadow, which carries out projection, can reach better viewing effect；And the subject belonging to the subject of question is when being geometry, due to
Geometric figure is solid figure, if being projected in a manner of plane projection, can understand student that answer causes certain difficulty,
The purpose for providing and solving a problem for student is provided；And projected in a manner of tripleplane, student can be from different perspectives to projection
Three-dimensional geometric shapes out are understood, the problem of encountering is made to be more easier to answer.
For another example when the affiliated subject of subject of question is geographical, due to being all much geographically about mountainous region, ocean, gas
The research such as time possibly can not allow student to have intuitive experience if projecting answer content in a manner of plane projection.As student exists
When understanding the landform such as karst landform, "Danxia" landform, coastal landform, glacial landforms, if projecting correlation in a manner of plane projection
Picture, student may the characteristic of all kinds of topography and geomorphologies can not be understood completely, thus be not easy distinguish different terrain landforms, and
Answer content is projected in a manner of tripleplane, student can from different angles observe various landforms, it is easier to area
Divide the feature of different terrain landforms.
As shown in figure 5, the present invention also provides a kind of embodiment of smart machine, smart machine includes:
Whether speech detection module 6 for the voice messaging of monitoring users, and detects in the voice messaging containing enquirement
Keyword；
The speech detection module 6 detects in the voice messaging if being also used to the smart machine without containing enquirement
Keyword then continues the voice messaging of monitoring users；
Control module 7 is electrically connected with the speech detection module 6, is mentioned for that ought identify to contain in the voice messaging
When asking keyword, photographing module 1 is opened.
The photographing module 1 is also electrically connected, for obtaining using the edge of the books detected as boundary with the control module 7
Take the interface image of books；
Region identification module 10 is putd question to, is electrically connected with the photographing module 1, for being examined from the interface image of the books
It measures target and is directed toward region, and the target is directed toward the corresponding image in region as the enquirement area image.
Parsing module 2 is electrically connected with the photographing module 1, enquirement region identification module 10, is used for from the photographing module
Subject of question is parsed in the 1 enquirement area image obtained；
Answer obtains module 3, is electrically connected with the parsing module 2, for obtaining in the corresponding answer of the subject of question
Hold；
Projection information generation module 4 obtains module 3 with the answer and is electrically connected, for being generated according to the answer content
Projection information；
The projection module 5, for when user selects the projection pattern to project for LED, the smart machine to pass through
The projection information is projected to default view field with LED mode of delivery by projection module 5；
Or for when user select the projection pattern as light projection, the smart machine pass through projection module 5 with
The projection information is projected to default view field by light projection mode；
Or for when user selects the projection pattern to project for 3D holography, the smart machine to pass through projection module 5
The projection information is projected to default view field with 3D holography mode of delivery；
Or for when user selects the projection pattern to project for AR, the smart machine to be by projection module 5 with AR
The projection information is projected to default view field by mode of delivery.
Logging modle 8 is electrically connected with the parsing module 2, forms enquirement record for recording described problem content；
Searching module 9 is electrically connected with the logging modle 8, searches whether exist and institute in record for puing question in history
It states problem content and approximately puts question to record；
The projection module 5 is electrically connected with the searching module 9, is existed and institute if being also used to put question in record in history
The similar enquirement record of problem content is stated, then the similar enquirement is recorded into corresponding subject of question and answer content projection
To the default view field.
Specifically, when student encounters problems during learning or inscribing, it can be with finger to the topic being ignorant of, then
Say: " how this problem does " or " how the first topic is done " etc. are similar to put question to language.Speech detection module 6 in smart machine includes wheat
Gram wind, can obtain the voice messaging of user, while the voice messaging of user is converted to text information；Then judge text information
In whether containing put question to keyword (such as the keywords such as " how doing ", " how doing ").
When smart machine is listened in the voice messaging of user containing keyword is putd question to, it can be obtained by photographing module 1
Take enquirement area image., firstly, the photographing module 1 of smart machine obtains the interface of books using the edge for detecting books as boundary
Then image detects that target is directed toward region from the interface image of the books, and target direction region is corresponding
Image is as the enquirement area image.In order to preferably identify the books on desktop, books identification model, this reality can be trained
Example is applied for training Unet parted pattern.It will be based on tensorflow deep learning frame, building Unet divides network.In order to
The size of segmentation network is reduced, the efficiency of segmentation network is promoted, modifies existing lightweight mobilenet_v2 network structure, it will
It is used for unet network code part, and unet decoded portion uses simple convolutional neural networks.
A variety of single desktop pictures and a variety of single book images can be acquired before training, by each Zhang Danyi desk-top picture
Picture and each Zhang Danyi book image carry out multiple combinations and (such as are placed in single book image on single book image not
Same position), the combination image of several single book images and single desktop picture is obtained, then by several combination images with 4:1
It is divided into training set and verifying collection, training set is divided into network by Unet and is trained, when Unet network is in training set and test
When IOU (gauge of segmentation network) value on collection is both greater than 0.95, Unet parted pattern is obtained.
After photographing module 1 obtains desktop picture, binary segmentation is carried out to desktop picture by Unet parted pattern, is obtained
The binary segmentation figure of desktop picture, and the edge of books is extracted from the binary segmentation figure of desktop picture, so that it is determined that publishing books
This position, gets the interface image of books from desktop picture.
Smart machine can be identified from interface image after getting the interface image of books by image recognition technology
The finger of user out, and region pointed by finger tip is defined as target and is directed toward region, then target is directed toward to the image in region
As enquirement area image.
In the present embodiment, smart machine can send subject of question after parsing subject of question in enquirement area image
To server, knowledge base can be stored in advance in server end, server can be searched corresponding according to subject of question in knowledge base
Content is answered, and answer content is returned into smart machine.
Projection module 5, such as Miniature projector can be equipped on smart machine.Smart machine can be according to preset projection template
(including: answer column, parsing column, knowledge point column) will answer corresponding content in content and be added to each of projection template
In a column, to generate projection information.User can preset projection module 5 projection pattern (including LED projection, light
Projection, 3D holography projection, AR projection), projection information is projected to default view field.A variety of projections are provided in the present embodiment
Mode can meet the projection demand of different projection contents for user's selection.
User can be asked a question and be recorded by smart machine, formed put question to record, when user is subsequent inquire again it is similar
It, can be by close problem and answer content push to user when problem.Such as content is " ' one hundred days when user's what is heard the problem of
Next sentence near the mountain to the greatest extent ' is _ _ _ _ ", and user also asked " upper one of ' attaining a yet higher goal ' is _ _ _ _ " in the past, then, intelligence
Similar enquirement can be recorded corresponding subject of question and answer content is all projected by equipment after projecting answer information to user
To default view field, deepen cognition of the user to similar knowledge point.
In addition, when projection module 5 needs to project the stereo-pictures such as geometric figure or kinds of experiments equipment, this implementation
Example considers that student can often have mapping, even auxiliary line, the operation such as add other figures when doing geometry topic, when doing experimental problem,
It is frequently necessary to for a variety of equipment being combined, while student is more complete, comprehensively checks the geometric figure being projected out in order to make,
There can be more intuitive experience when testing, this programme increases edit operation when being projected in a manner of tripleplane,
User can be edited accordingly on the 3-D image projected, be best understood from learning Content with this.
For example, when the time for touching arbitrary point on the 3-D image reaching the first preset time, or work as described in touching
On 3-D image at any at least 3, it is image drag operation that the smart machine, which parses the edit operation, and according to
The image drag operation at family drags 3-D image；
When the time for touching arbitrary point on the 3-D image reaching the second preset time, the smart machine parses institute
Edit operation is stated as image rotation operation, and 3-D image is rotated according to the operation of the image rotation of user.
When any two points on the touching 3-D image, and when two touch points distance diminutions, the smart machine solution
The edit operation is analysed as image down operation；When touching any two points on the 3-D image, and two touch points distances
When becoming larger, the smart machine parses the edit operation as image amplifying operation；
Reach the 4th preset time when the time for touching any point on the 3-D image, and touch points moving distance is big
When pre-determined distance, it is to make graphic operation that the smart machine, which parses the edit operation,；
When user clutches a certain figure in the 3-D image, the smart machine parses the editor behaviour
It is operated as image-erasing；And add when the speech detection module 6 of smart machine listens in the voice messaging of user comprising figure
When adding information, then the corresponding figure of the figure addition information is added in 3-D image, such as user says " addition cylindrical body ",
Smart machine can analyze by semantic understanding when listening to the words and need to add " cylindrical body " this figure.
The smart machine includes intelligent desk lamp, and the photographing module and the projection module are arranged in the intelligent desk lamp
Head, and the camera shooting direction of the photographing module and the projecting direction of the projection module are towards the bottom of the intelligent desk lamp
Seat；Or；The smart machine includes intelligent wall lamp, the photographing module and projection module setting in the intelligent wall lamp
On, and the camera shooting direction of the photographing module and the projecting direction of the projection module are towards the default view field；Or；
The smart machine includes intelligent pendent lamp, the photographing module and projection module setting on the intelligent pendent lamp, and institute
The camera shooting direction of photographing module and the projecting direction of the projection module are stated towards the default view field.
As shown in fig. 6, the intelligent desk lamp ontology includes desk lamp bottom the present invention provides a kind of schematic diagram of intelligent desk lamp
Seat, connecting rod, desk lamp head；Camera setting is on the desk lamp head, and the camera shooting direction of the camera is towards institute
State Desk lamp feet side；The microphone and loudspeaker are separately positioned on the Desk lamp feet.When student's study is met difficulty,
Can through the foregoing embodiment in smart machine assisted learning function, complete autonomous learning.
It should be noted that above-described embodiment can be freely combined as needed.The above is only of the invention preferred
Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, several improvements and modifications can also be made, these modifications and embellishments should also be considered as the scope of protection of the present invention.
Claims (10)
1. a kind of exchange method based on smart machine, which is characterized in that comprising steps of
When smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine passes through photographing module
It obtains and puts question to area image；
The smart machine parses subject of question from the enquirement area image that the photographing module obtains, and obtains institute
State the corresponding answer content of subject of question；
The smart machine generates projection information according to the answer content, and according to the projection pattern of user's selection by the throwing
Shadow information is projected to default view field.
2. a kind of exchange method based on smart machine according to claim 1, which is characterized in that when smart machine is monitored
When into the voice messaging of user containing keyword is putd question to, the smart machine is obtained by photographing module and puts question to area image,
It is further comprised the steps of: before this step
The voice messaging of smart machine monitoring users, and whether detect in the voice messaging containing enquirement keyword；
If the smart machine detects to continue the language of monitoring users without containing the enquirement keyword in the voice messaging
Message breath；
If the smart machine detects to open photographing module containing the enquirement keyword in the voice messaging.
3. a kind of exchange method based on smart machine according to claim 1, which is characterized in that when smart machine identifies
When out in the voice messaging of user containing puing question to keyword, the smart machine is obtained by photographing module and puts question to area image,
This step specifically includes:
When smart machine identifies in the voice messaging of user containing keyword is putd question to, the smart machine opens camera shooting mould
Block obtains the interface image of books using the edge for detecting books as boundary；
The smart machine detects that target is directed toward region from the interface image of the books, and the target is directed toward region
Corresponding image is as the enquirement area image.
4. a kind of exchange method based on smart machine according to any one of claim 1-3, which is characterized in that with
The projection information is projected to default view field by the projection pattern of family selection, this step specifically includes:
When user selects the projection pattern to project for LED, the smart machine will with LED mode of delivery by projection module
The projection information is projected to default view field；
When user selects the projection pattern as light projection, the smart machine is by projection module in a manner of light projection
The projection information is projected to default view field；
When user selects the projection pattern to project for 3D holography, the smart machine is by projection module with 3D holography projection
The projection information is projected to default view field by mode；
When user selects the projection pattern as AR projection, the smart machine is by projection module with AR mode of delivery by institute
It states projection information and is projected to default view field.
5. a kind of exchange method based on smart machine according to any one of claim 1-3, which is characterized in that also wrap
Include step:
Smart machine record described problem content, which is formed, puts question to record, and history put question to search whether to exist in record with
Described problem content approximately puts question to record；
If being putd question in record in history and there is enquirement similar with described problem content record, the similar enquirement is recorded
Corresponding subject of question and answer content are projected to the default view field.
6. a kind of smart machine characterized by comprising
Photographing module, for obtaining and puing question to area when smart machine identifies in the voice messaging of user containing keyword is putd question to
Area image；
Parsing module is electrically connected with the photographing module, for from the enquirement area image that the photographing module obtains
Parse subject of question；
Answer obtains module, is electrically connected with the parsing module, for obtaining the corresponding answer content of the subject of question；
Projection information generation module obtains module with the answer and is electrically connected, for generating projection letter according to the answer content
Breath；
Projection module is electrically connected with the projection information generation module, and the projection pattern for being selected according to user is by the throwing
Shadow information is projected to default view field.
7. a kind of smart machine according to claim 6, it is characterised in that:
The smart machine includes intelligent desk lamp, and the head of the intelligent desk lamp is arranged in the photographing module and the projection module
Portion, and the photographing module camera shooting direction and the projection module projecting direction towards the intelligent desk lamp pedestal one
Side；
Or；The smart machine includes intelligent wall lamp, the photographing module and projection module setting in the intelligent wall lamp
On, and the camera shooting direction of the photographing module and the projecting direction of the projection module are towards the default view field one
Side；
Or；The smart machine includes intelligent pendent lamp, the photographing module and projection module setting in the intelligent pendent lamp
On, and the camera shooting direction of the photographing module and the projecting direction of the projection module are towards the default view field one
Side.
8. a kind of smart machine according to claim 6, which is characterized in that the smart machine further include:
Whether speech detection module for the voice messaging of monitoring users, and detects crucial containing puing question in the voice messaging
Word；
The speech detection module detects in the voice messaging if being also used to the smart machine without containing enquirement key
Word then continues the voice messaging of monitoring users；
Control module is electrically connected with the speech detection module, for crucial containing puing question in the voice messaging when identifying
When word, photographing module is opened；
The photographing module is also electrically connected with the control module, for obtaining books using the edge of the books detected as boundary
Interface image；
Region identification module is putd question to, is electrically connected with the photographing module, for detecting mesh from the interface image of the books
Mark is directed toward region, and the target is directed toward the corresponding image in region as the enquirement area image.
9. a kind of smart machine a method according to any one of claims 6-8, it is characterised in that:
The projection module, for when user selects the projection pattern to project for LED, the smart machine to pass through projective module
The projection information is projected to default view field with LED mode of delivery by block；
Or for when user selects the projection pattern as light projection, the smart machine to be thrown by projection module with light
It penetrates mode and the projection information is projected to default view field；
Or for when user selects the projection pattern to project for 3D holography, the smart machine to be complete with 3D by projection module
It ceases mode of delivery and the projection information is projected to default view field；
Or for when user selects the projection pattern to project for AR, the smart machine to be by projection module with the projection side AR
The projection information is projected to default view field by formula.
10. a kind of smart machine a method according to any one of claims 6-8, which is characterized in that the smart machine also wraps
It includes:
Logging modle forms enquirement record for recording described problem content；
Searching module is electrically connected with the logging modle, searches whether to exist in record and described problem for puing question in history
Content approximately puts question to record；
The projection module is electrically connected with the searching module, is existed and described problem if being also used to put question in record in history
Content similar enquirement record, then by the similar enquirement record corresponding subject of question and answer content be projected to it is described
Default view field.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811015615.6A CN109191940B (en) | 2018-08-31 | 2018-08-31 | Interaction method based on intelligent equipment and intelligent equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811015615.6A CN109191940B (en) | 2018-08-31 | 2018-08-31 | Interaction method based on intelligent equipment and intelligent equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109191940A true CN109191940A (en) | 2019-01-11 |
| CN109191940B CN109191940B (en) | 2021-09-24 |
Family
ID=64917560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811015615.6A Active CN109191940B (en) | 2018-08-31 | 2018-08-31 | Interaction method based on intelligent equipment and intelligent equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109191940B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753583A (en) * | 2019-01-16 | 2019-05-14 | 广东小天才科技有限公司 | One kind searching topic method and electronic equipment |
| CN109947977A (en) * | 2019-03-13 | 2019-06-28 | 广东小天才科技有限公司 | A kind of intension recognizing method and device, terminal device of combination image |
| CN110489746A (en) * | 2019-07-31 | 2019-11-22 | 深圳市优必选科技股份有限公司 | A kind of information extracting method, information extracting device and intelligent terminal |
| CN111709414A (en) * | 2020-06-29 | 2020-09-25 | 济南浪潮高新科技投资发展有限公司 | AR device, character recognition method and device thereof, and computer-readable storage medium |
| CN111739028A (en) * | 2020-05-26 | 2020-10-02 | 华南理工大学 | Nail region image acquisition method, system, computing device and storage medium |
| CN112184501A (en) * | 2019-07-02 | 2021-01-05 | 广东小天才科技有限公司 | Remote tutoring method and device, terminal equipment and computer readable storage medium |
| CN112233470A (en) * | 2019-06-28 | 2021-01-15 | 广东小天才科技有限公司 | Learning note generation method and intelligent device |
| CN112735413A (en) * | 2020-12-25 | 2021-04-30 | 浙江大华技术股份有限公司 | Instruction analysis method based on camera device, electronic equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1135027A (en) * | 1965-11-29 | 1968-11-27 | William Philip Exton Jr | Ability testing apparatus |
| CN101986293A (en) * | 2010-09-03 | 2011-03-16 | 百度在线网络技术（北京）有限公司 | Method and equipment for displaying search answer information on search interface |
| CN103748623A (en) * | 2011-05-17 | 2014-04-23 | Pt艾伦特有限公司 | Child-directed learning system integrating cellular communication, education, entertainment, alert and monitoring systems |
| CN104143163A (en) * | 2014-08-04 | 2014-11-12 | 兴天通讯技术（天津）有限公司 | Generating method and device for knowledge map |
| US20140341473A1 (en) * | 2011-12-06 | 2014-11-20 | Kyungpook National University Industry-Academic Cooperation Foundation | Apparatus and method for enhancing user recognition |
| CN104253904A (en) * | 2014-09-04 | 2014-12-31 | 广东小天才科技有限公司 | Method and smartphone for implementing reading learning |
| CN105975560A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Question searching method and question searching apparatus for intelligent device |
| CN106228982A (en) * | 2016-07-27 | 2016-12-14 | 华南理工大学 | A kind of interactive learning system based on education services robot and exchange method |
| CN106781737A (en) * | 2017-01-13 | 2017-05-31 | 河南工业大学 | A kind of scene-type tutoring system and method |
| CN206555794U (en) * | 2017-03-15 | 2017-10-13 | 林钊鸿 | A kind of intelligent translation desk lamp |
| CN206789081U (en) * | 2017-03-23 | 2017-12-22 | 东莞市三木光电科技有限公司 | A kind of electrical educational appliance for childern |
| CN107992507A (en) * | 2017-03-09 | 2018-05-04 | 北京物灵智能科技有限公司 | A kind of child intelligence dialogue learning method, system and electronic equipment |
| CN108021637A (en) * | 2017-11-28 | 2018-05-11 | 广东小天才科技有限公司 | A kind of topic searching method, device, facility for study and storage medium |
| CN108182270A (en) * | 2018-01-17 | 2018-06-19 | 广东小天才科技有限公司 | Search for content transmission and searching method, smart pen, search terminal and storage medium |
| CN108287903A (en) * | 2018-01-25 | 2018-07-17 | 广东小天才科技有限公司 | It is a kind of to search topic method and smart pen with what projection was combined |
-
2018
- 2018-08-31 CN CN201811015615.6A patent/CN109191940B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1135027A (en) * | 1965-11-29 | 1968-11-27 | William Philip Exton Jr | Ability testing apparatus |
| CN101986293A (en) * | 2010-09-03 | 2011-03-16 | 百度在线网络技术（北京）有限公司 | Method and equipment for displaying search answer information on search interface |
| CN103748623A (en) * | 2011-05-17 | 2014-04-23 | Pt艾伦特有限公司 | Child-directed learning system integrating cellular communication, education, entertainment, alert and monitoring systems |
| US20140341473A1 (en) * | 2011-12-06 | 2014-11-20 | Kyungpook National University Industry-Academic Cooperation Foundation | Apparatus and method for enhancing user recognition |
| CN104143163A (en) * | 2014-08-04 | 2014-11-12 | 兴天通讯技术（天津）有限公司 | Generating method and device for knowledge map |
| CN104253904A (en) * | 2014-09-04 | 2014-12-31 | 广东小天才科技有限公司 | Method and smartphone for implementing reading learning |
| CN105975560A (en) * | 2016-04-29 | 2016-09-28 | 广东小天才科技有限公司 | Question searching method and question searching apparatus for intelligent device |
| CN106228982A (en) * | 2016-07-27 | 2016-12-14 | 华南理工大学 | A kind of interactive learning system based on education services robot and exchange method |
| CN106781737A (en) * | 2017-01-13 | 2017-05-31 | 河南工业大学 | A kind of scene-type tutoring system and method |
| CN107992507A (en) * | 2017-03-09 | 2018-05-04 | 北京物灵智能科技有限公司 | A kind of child intelligence dialogue learning method, system and electronic equipment |
| CN206555794U (en) * | 2017-03-15 | 2017-10-13 | 林钊鸿 | A kind of intelligent translation desk lamp |
| CN206789081U (en) * | 2017-03-23 | 2017-12-22 | 东莞市三木光电科技有限公司 | A kind of electrical educational appliance for childern |
| CN108021637A (en) * | 2017-11-28 | 2018-05-11 | 广东小天才科技有限公司 | A kind of topic searching method, device, facility for study and storage medium |
| CN108182270A (en) * | 2018-01-17 | 2018-06-19 | 广东小天才科技有限公司 | Search for content transmission and searching method, smart pen, search terminal and storage medium |
| CN108287903A (en) * | 2018-01-25 | 2018-07-17 | 广东小天才科技有限公司 | It is a kind of to search topic method and smart pen with what projection was combined |
Non-Patent Citations (2)
| Title |
|---|
| （美）基珀等: "《增强现实技术导论》", 31 August 2016, 国防工业出版社 * |
| 丁梅芊、金小湘: "《互联网下的改变》", 30 October 2016, 辽宁大学出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109753583A (en) * | 2019-01-16 | 2019-05-14 | 广东小天才科技有限公司 | One kind searching topic method and electronic equipment |
| CN109947977A (en) * | 2019-03-13 | 2019-06-28 | 广东小天才科技有限公司 | A kind of intension recognizing method and device, terminal device of combination image |
| CN112233470A (en) * | 2019-06-28 | 2021-01-15 | 广东小天才科技有限公司 | Learning note generation method and intelligent device |
| CN112184501A (en) * | 2019-07-02 | 2021-01-05 | 广东小天才科技有限公司 | Remote tutoring method and device, terminal equipment and computer readable storage medium |
| CN110489746A (en) * | 2019-07-31 | 2019-11-22 | 深圳市优必选科技股份有限公司 | A kind of information extracting method, information extracting device and intelligent terminal |
| CN111739028A (en) * | 2020-05-26 | 2020-10-02 | 华南理工大学 | Nail region image acquisition method, system, computing device and storage medium |
| CN111709414A (en) * | 2020-06-29 | 2020-09-25 | 济南浪潮高新科技投资发展有限公司 | AR device, character recognition method and device thereof, and computer-readable storage medium |
| CN112735413A (en) * | 2020-12-25 | 2021-04-30 | 浙江大华技术股份有限公司 | Instruction analysis method based on camera device, electronic equipment and storage medium |
| CN112735413B (en) * | 2020-12-25 | 2024-05-31 | 浙江大华技术股份有限公司 | Instruction analysis method based on camera device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109191940B (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109191940A (en) | A kind of exchange method and smart machine based on smart machine | |
| CN109005632A (en) | A kind of assisted learning method and intelligent desk lamp | |
| CN109191939A (en) | A kind of tripleplane's exchange method and smart machine based on smart machine | |
| US11321583B2 (en) | Image annotating method and electronic device | |
| CN109272997A (en) | A kind of smart machine and its projection interactive method | |
| US11410570B1 (en) | Comprehensive three-dimensional teaching field system and method for operating same | |
| Schiel et al. | The SmartKom Multimodal Corpus at BAS. | |
| CN109035919B (en) | Intelligent device and system for assisting user in solving problems | |
| CN111027486A (en) | Auxiliary analysis and evaluation system and method for big data of teaching effect of primary and secondary school classroom | |
| CN106599881A (en) | Student state determination method, device and system | |
| CN106773820B (en) | Robot interactive approach, device and robot | |
| CN113835522A (en) | Sign language video generation, translation and customer service method, device and readable medium | |
| KR20090097891A (en) | Controlling a document based on user behavioral signals detected from a 3d captured image stream | |
| CN107924392A (en) | Annotation based on posture | |
| CN110085068A (en) | A kind of study coach method and device based on image recognition | |
| CN109243215A (en) | A kind of exchange method based on intelligent apparatus, intelligent apparatus and system | |
| CN117055724B (en) | Working method of generating teaching resource system in virtual teaching scene | |
| EP4075411A1 (en) | Device and method for providing interactive audience simulation | |
| CN109377795A (en) | A kind of the study exchange method and smart machine of smart machine | |
| CN110245253A (en) | A kind of Semantic interaction method and system based on environmental information | |
| CN111539408A (en) | Intelligent point reading scheme based on photographing and object recognizing | |
| CN111539339A (en) | Data processing method and device, electronic equipment and storage medium | |
| JP2014085998A (en) | Electronic note creation support device and program for electronic note creation support device | |
| CN110491384A (en) | A kind of voice data processing method and device | |
| CN110084187A (en) | Location recognition method, device, equipment and storage medium based on computer vision |
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 |