CN109345906A - A kind of artificial intelligence deep learning realize system and method - Google Patents
A kind of artificial intelligence deep learning realize system and method Download PDFInfo
- Publication number
- CN109345906A CN109345906A CN201811068037.2A CN201811068037A CN109345906A CN 109345906 A CN109345906 A CN 109345906A CN 201811068037 A CN201811068037 A CN 201811068037A CN 109345906 A CN109345906 A CN 109345906A
- Authority
- CN
- China
- Prior art keywords
- phrase
- picture
- deep learning
- artificial intelligence
- learned
- 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
- G09B19/00—Teaching not covered by other main groups of this subclass
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to Internet technical field, the invention discloses a kind of artificial intelligence deep learning realizes system and method, comprising: picture storage module, for store picture to be learned and with the one-to-one matching area of picture to be learned；Phrase memory module, for storing phrase, the phrase includes phrase corresponding with the picture to be learned；Correct matching memory module, the matching relationship including the matching area and the phrase；Mobile module, for the phrase to be moved to the matching area；Transmission unit；Server, the server include first judgment module, and for judging whether the phrase for being moved to the matching area is correct, if correctly, providing correct prompt, if incorrect, the phrase returns to original position.Artificial intelligence of the invention deep learning realize that the phrase of student may be implemented and the matched of picture judges automatically and improve the deep learning learning efficiency of student in system.
Description
Technical field
The present invention relates to Internet technical fields, and in particular to a kind of artificial intelligence deep learning realize system and side
Method.
Background technique
The present invention belongs to the relevant technologies related to the present invention for the description of background technique, be only used for explanation and just
In understanding the contents of the present invention, should not be construed as applicant be specifically identified to or estimate applicant be considered the present invention be put forward for the first time
The prior art of the applying date of application.
Education is played the role of vital in social progress, and how to do the educational work of good student is today's society
Important topic.
For the study of the knowledge figure of child and foreign language, how to realize that the phrase of student and the matched of picture judge automatically
Become current urgent problem to be solved with the learning efficiency for improving student.
Summary of the invention
The purpose of the embodiment of the present invention is that deep learning realizes that system and method, the present invention are real with providing a kind of artificial intelligence
A kind of artificial intelligence of example offer is provided deep learning realize system may be implemented student phrase and picture it is matched automatic
Judgement and the learning efficiency for improving student.
The purpose of the embodiment of the present invention is that be achieved through the following technical solutions:
In a first aspect, the embodiment of the invention provides a kind of artificial intelligence deep learning realizes system, comprising:
Picture storage module, for store picture to be learned and with the one-to-one Matching band of picture to be learned
Domain；
Phrase memory module, for storing phrase, the phrase includes phrase corresponding with the picture to be learned；
Correct matching memory module, the matching relationship including the matching area and the phrase；
Mobile module, for the phrase to be moved to the matching area；
Transmission unit, for the mobile data of the mobile module to be sent to server；
Server, the server include first judgment module, the word for judging to be moved to the matching area
Whether group is correct,
If correct, correct prompt is provided,
If incorrect, the phrase returns to original position.
Further, a kind of artificial intelligence deep learning realize system further include:
Grading module, for scoring after the matching area is matched with correct phrase.
Further, the marking mode that the grading module uses are as follows:
If the number that phrase returns to original position is 0, score is full marks, is denoted as M；
If phrase, which returns to original position number, is greater than 0, scored using formula (1):
Wherein,
M0- score；
N-matching times；
N0- matching area number；
M-full marks.
The number of the P-phrase that mistake is crossed in the past and this time mistake is crossed again；
The number of errors of the more difficult vocabulary of R-.
Further, a kind of artificial intelligence deep learning realize system further include:
Second judgment module, for judging whether mobile number is greater than first threshold, if mobile number is greater than described the
One threshold value, then terminate.
Further, the first threshold is 2 times of matching area number.
Further, the mobile data that the transmission unit is sent is result data.
Second aspect, the embodiment of the invention provides a kind of artificial intelligence deep learning realizes the implementation method of system,
A kind of artificial intelligence deep learning realize system for above-mentioned any artificial intelligence deep learning realization system,
The implementation method includes the following steps:
Phrase is moved to matching area；
Whether the judgement phrase picture match corresponding with matching area is correct；
If correct, correct prompt is provided, if incorrect, phrase returns to original position.
According to the above aspect of the present invention, a kind of artificial intelligence of the present invention deep learning realize system and at least have following beneficial to effect
Fruit:
A kind of artificial intelligence of the application deep learning realize system by first judgment module to matching result carry out
After judging to artificial intelligence, original position correctly or by picture is directly returned to according to judging result prompt, in this way, can in student's study
To carry out deep learning according to the prompt of system.
A kind of artificial intelligence of the application deep learning realize system scoring according to matching times and picture (Matching band
Domain) quantity give a mark, fully considered the factor of picture number, provide reasonable marking.
The application is also provided with the threshold value of matching times, can prevent student from carrying out random to picture and phrase in this way
Match, without studying hard, prevents the waste of teaching resource.
Transmission unit only sends result data in the application, without transmission process data, is effectively reduced server
Pressure.
Detailed description of the invention
It, below will be to attached drawing needed in embodiment description in order to illustrate more clearly of technical solution of the present invention
It is briefly described:
For a kind of artificial intelligence of the present invention deep learning realizes a kind of artificial intelligence in one embodiment of system and method to Fig. 1
The structural schematic diagram of ground deep learning realization system；
For a kind of artificial intelligence of the present invention deep learning realizes a kind of artificial intelligence in another embodiment of system and method to Fig. 2
Energy ground deep learning realizes the structural schematic diagram of system；
For a kind of artificial intelligence of the present invention deep learning realizes a kind of artificial intelligence in the another embodiment of system and method to Fig. 3
Energy ground deep learning realizes the structural schematic diagram of system；
For a kind of artificial intelligence of the present invention deep learning realizes a kind of artificial intelligence in one embodiment of system and method to Fig. 4
Ground deep learning realizes network system realization flow chart；
For a kind of artificial intelligence of the present invention deep learning realizes a kind of artificial intelligence in another embodiment of system and method to Fig. 5
It can ground deep learning realization network system realization flow chart.
Fig. 6 be a kind of artificial intelligence of the present invention deep learning realize system mobile module first state vertical view
Figure；
Fig. 7 be a kind of artificial intelligence of the present invention deep learning realize system mobile module the second state vertical view
Figure；
Fig. 8 is the partial enlarged view of Fig. 7；
Fig. 9 is the partial enlarged view on the top of Fig. 8；
Figure 10 is the partial enlarged view of the lower part of Fig. 8；
Figure 11 is the main view of Fig. 6；
Figure 12 is the main view of Fig. 7.
Specific embodiment
The present invention is further discussed in detail with reference to the accompanying drawings and examples, it should be understood that attached drawing and implementation
Example is technical solution of the present invention to be easier to understand for those skilled in the art, and cannot function as the limit of the scope of the present invention
It is fixed.
In following introductions, term " first ", " second " only for descriptive purposes, and should not be understood as instruction or dark
Show relative importance.Following introductions provide multiple embodiments of the invention, can replace or merge between different embodiments
Combination, therefore the present invention is it is also contemplated that all possible combinations comprising documented identical and/or different embodiments.Thus, such as
Fruit one embodiment include feature A, B, C, another embodiment include feature B, D, then the present invention also should be regarded as include containing
A, the every other possible combined embodiment of one or more of B, C, D, although the embodiment may be in the following contents
In have specific literature record.
For artificial intelligence a kind of in one embodiment of the invention deep learning realizes system structure diagram to Fig. 1, such as Fig. 1 institute
Show, a kind of artificial intelligence of the embodiment of the present invention deep learning realize system include:
Picture storage module 101, for storing picture to be learned and being matched correspondingly with the picture to be learned
Region；
Phrase memory module 102, for storing phrase, the phrase includes word corresponding with the picture to be learned
Group；
Correct matching memory module 103, the matching relationship including the matching area and the picture to be learned；
Mobile module 104, for the picture to be learned to be moved to the matching area；
Transmission unit 105, for the mobile data of the mobile module to be sent to server；
Server 106, the server include first judgment module, are moved to the matching area for judging
Whether picture to be learned is correct,
If correct, correct prompt is provided,
If incorrect, the phrase returns to original position.
A kind of artificial intelligence of the application deep learning realize system by first judgment module to matching result carry out
After judgement, original position correctly or by picture is directly returned to according to judging result prompt, in this way, can be according to system in student's study
Prompt learnt automatically.
For artificial intelligence a kind of in another embodiment of the present invention deep learning realizes system structure diagram, such as Fig. 2 to Fig. 2
It is shown, a kind of artificial intelligence deep learning realize that system includes:
Picture storage module 101, for storing picture to be learned and being matched correspondingly with the picture to be learned
Region；
To note here is that: the embodiment of the present invention is not specifically limited the type of picture to be learned, as long as can expire
The needs that podolite is practised are preferably adapted for the picture of age bracket study, if kindergarten baby learns some simple pictures, such as
Scene, fruit, stationery, vehicles etc..
Phrase memory module 102, for storing phrase, the phrase includes word corresponding with the picture to be learned
Group；
To note here is that: the embodiment of the present invention is not especially limited the type of phrase, as long as can satisfy study
It needs, in some embodiments of the invention, phrase can select Chinese, English, Japanese or German etc., according to not classmate
Practise the different language of Demand Design.
Correct matching memory module 103, the matching relationship including the matching area and the phrase；
To note here is that: each matching area is corresponding with a picture, and phrase corresponding with picture is uniquely, only
Correct picture to be learned is moved to matching area, server will judge the secondary matching.
Mobile module 104, for the picture to be learned to be moved to the matching area；
Transmission unit 105, for the mobile data of the mobile module to be sent to server；
Server 106, the server include first judgment module, are moved to the matching area for judging
Whether picture to be learned is correct,
If correct, correct prompt is provided,
If incorrect, the phrase returns to original position；
To note here is that: it provides the mode correctly prompted and is not especially limited, can be voice, such as " answer just
Really ", " GOOD ", " stick is rattled away " etc., can be corresponding text, can also play while voice plays certainly corresponding dynamic
It draws, the enjoyment of student's study can be improved in this way.
Grading module 107, for scoring after the matching area is matched with correct picture to be learned.
In some embodiments of the invention, the marking mode that the grading module uses are as follows:
If the number that phrase returns to original position is 0, score is full marks, is denoted as M；
If phrase, which returns to original position number, is greater than 0, scored using formula (1):
Wherein,
M0- score；
N-matching times；
N0- matching area number；
M-full marks.
The number of the P-phrase that mistake is crossed in the past and this time mistake is crossed again；
The number of errors of the more difficult vocabulary of R-.
The number P, more difficult for the phrase that mistake is crossed before the present invention introduces in traditional algorithm and this time mistake is crossed again
The number of errors R of vocabulary, so that final score is corrected with corresponding 20%, 10% weight, to be truly reflected user's
Practical cognitive ability and learning ability, more accurately to embody its learning ability.
Wherein, due to picture to be learned and phrase be it is one-to-one, mistake is crossed in the past and this time mistake is crossed again
The number P of phrase, that is the number P for the picture to be learned that mistake is crossed in the past and this time mistake is crossed again, similarly, it is more difficult to vocabulary
Number of errors R, that is the number of errors of more difficult picture to be learned.
Wherein, such as full marks M is 100 points, and matching times N is 100 times, matching area number N0It is 82 times, that is, phrase returns
Returning original position number is 18 times, and the number P for the phrase that mistake is crossed in the past and this time mistake is crossed again is 2, it is more difficult to the mistake of vocabulary
Number R is 2, then score M0It is 85.608.To have better referential, help compared to 82 points in traditional algorithm
Teacher Yu understands the study condition of child, and more reasonably carries out ranking for student.
Wherein, the more difficult vocabulary can be gap vocabulary, for example, user is pupil, and the child in primary school's outline
Vocabulary other than the outline of garden can be more difficult vocabulary, in another example, user is junior school student, and other than primary school's outline in junior middle school's outline
Vocabulary can be more difficult vocabulary.The score of user can correspondingly, be minutely improved when the more difficult vocabulary of user's mistake is more, with
Just the weight of more difficult vocabulary is embodied, observes the study shape of student according to the score of user convenient for the ranking of student and teacher
Condition.
Wherein, the mistake in the past is crossed and this time wrong phrase crossed can be to repeat error vocabulary, for example, server exists again
The wrong phrase saved in database is compared with the existing phrase for returning to original position, if meeting, this is met
Number is calculated as P.
To note here is that: a kind of artificial intelligence of the embodiment of the present invention deep learning realize system scoring according to
Quantity with number and picture (matching area) is given a mark, and has been fully considered the factor of picture number, has been provided and reasonably beat
Point.
In the another embodiment of the present invention of the position Fig. 3 a kind of artificial intelligence deep learning realize system structure diagram, such as Fig. 3
It is shown, a kind of artificial intelligence deep learning realize system further include:
Second judgment module 108, for judging whether mobile number is greater than first threshold, if mobile number is greater than described
First threshold then terminates.
In some embodiments of the invention, the first threshold is 2 times of matching area number.
To note here is that: a kind of artificial intelligence of the embodiment of the present invention deep learning realize system be provided with matching
The threshold value of number, can prevent student from carrying out random fit to picture and phrase in this way prevents teaching resource without studying hard
Waste.
In some embodiments of the invention, the mobile data that the transmission unit is sent is result data.
To note here is that: the transmission unit 105 in the embodiment of the present invention only sends result data, and for process
Data are not sent, and if student is during mobile phrase, the mobile route of phrase, the data such as movement speed, transmission unit is not
Relevant operating process is sent to server, and only sends result data, such as the position of final picture, mobile number etc., in this way
The pressure of server can effectively be mitigated, save resource.
Preferably, as figures 6 to 12 show, referring to Fig. 6,8,9,11, the mobile module includes screen shell 101, touch screen
102, penholder 110, stylus 120, the first guide rail 121, region ring 130, region lock 200, the screen shell 101 is fixed with touch
Screen 102, the both ends of the screen shell 101 and the penholder 110 are fixed, and the middle part of the penholder 110 offers the along its side
One through-hole 111, the first through hole 111 is interior to be equipped with stylus 120, the first through hole 111 and at least four first guide rails 121
One end connection, the other end of at least four first guide rail 121 and the region ring 130 are fixed, the region ring 130
Region lock 200 is equipped at first guide rail 121, it is aobvious that at least four region rings 130 are arranged respectively at touch screen 102
At least four matching areas shown, the touch screen 102 at least four matching areas show different phrases respectively, described
Touch screen 102 at one through-hole 111 shows picture to be learned, the electricity of the server and the touch screen 102, region lock 200
Source module connection, when the phrase of the matching area at region lock 200 is with the picture match to be learned, then server opens area
Domain lock 200, when the phrase and the picture to be learned of the matching area at region lock 200 mismatch, then server closing area
Domain lock 200；
Referring to Fig. 9,10, the region lock 200 includes arc-shaped guide rail 201, the first electromagnet 202, arc ring 203, limit
The side surface of block 204, the arc-shaped guide rail 201 and the region ring 130 is fixed, and the region ring 130 is equipped with and described first
The second through-hole that guide rail 121 penetrates through, the side surface positioned at second through hole of the region ring 130 and the arc-shaped guide rail
201 is fixed, sets that there are two the first electromagnet 202 being moved along it, two first electromagnet on the arc-shaped guide rail 201
202 power module is connect with server, the surface of the middle line far from the arc-shaped guide rail 201 of first electromagnet 202
It is fixed with arc ring 203, the both ends of the arc-shaped guide rail 201 are equipped with limited block 204.
The present invention by above-mentioned penholder 110, first guide rail 121, region ring 130 can specification user slide touch screen 102
Track, also, can more intuitively allow user, especially primary school, kindergarten and user below for correct by region lock 200
, it is incorrect be matched with more intuitive feeling, so that user be helped more easily to carry out depth for picture and phrase
Study.
Wherein, limited block 204 can be made of plastics, irony, aluminum, resin material, and certainly, the limited block 204 can also
It is made of permanent magnet, thus when it is to close that region lock 200 is by server control, it can be for first by the first electromagnet 202
It is directly powered off after mutually exclusive, so that limited block 204 made of permanent magnet is allowed persistently to attract the first electromagnet 202, so that
When the first 202 no power of electromagnet, region lock 200 can be also allowed to be in close state, thus power saving.
Wherein, the arc ring 203 is coaxially disposed with the arc-shaped guide rail 201, also, the arc ring 203 with it is described
Arc length shared by first electromagnet 202 is that 3/16 perimeter to 1/4 perimeter is preferred, and such perimeter can be when region be locked 200 and closed, i.e.,
When server controls two the first electromagnet 202 repulsions, stylus 120 is made to cannot be introduced into matching area, and when region locks 200 dozens
When opening, i.e., when two the first electromagnet 202 of server control attract each other, stylus is enable to be moved to matching area, also,
The first electromagnet 202 to attract each other when two, still can pushing away by stylus 120 not in the middle line of arc-shaped guide rail 201
The stylus 120 is moved to matching area by power.
Wherein, the side positioned at second through hole of at least one end of the arc-shaped guide rail 201 and the region ring 130
Surface is fixed, certainly, can also both ends be secured to.To ensure that the round towards first guide rail of arc-shaped guide rail 201
121。
Wherein, the second through-hole penetrated through with first guide rail 121 that region ring 130 is equipped with can allow stylus 120 to be moved
It moves to region ring 130, or at least half is moved in region ring 130, and guarantees that stylus 120 can successfully slide back to first and lead
Rail 121.
The picture to be learned is slid into matching area by stylus 120 by the user, if matching, user can be straight
It sees ground stylus 120 is dragged in region lock 200, if mismatching, region lock 200 keeps stylus 120 outside of the door, or
It says, region lock 200 makes stylus 120 that can not be moved to matching area；
Wherein, the stylus 120 can be moved to from the first through hole 111 by first guide rail 121 described
The touch and sliding with touch screen 102 can be remained at region lock 200, also, in moving process.So realize above-mentioned function
Mode can be, the first through hole 111 be also penetrated through from the side of penholder 110, that is, can be regarded as the side of the penholder 110
Surface offers guide groove identical with the first through hole 111, and the guide groove is connect with first guide rail 121, and described first
Guide rail 121 can be configured by two or so the, body of rod that is parallel to each other or plate body are made, and at least four first guide rails 121 can be the
The axially different position of one guide rail 121 and the penholder 110 are fixed, so as to make user from least four first guide rails 121
Any one skids off stylus.
Second aspect, the embodiment of the invention provides a kind of artificial intelligence deep learning realizes the implementation method of system,
A kind of artificial intelligence deep learning realize system for above-mentioned any artificial intelligence deep learning realization system,
For artificial intelligence a kind of in one embodiment of the invention deep learning realizes network system realization flow chart to Fig. 4, such as
Shown in Fig. 4, the implementation method includes the following steps:
S101: picture to be learned is moved to matching area；
S102: judge whether the picture to be learned phrase matching corresponding with matching area is correct；
If correct, then follow the steps S103: providing correct prompt,
If incorrect, then follow the steps S104 phrase and return to original position.
For artificial intelligence a kind of in another embodiment of the present invention deep learning realizes network system realization flow chart to Fig. 5,
As shown in figure 5, the implementation method includes the following steps:
S101: picture to be learned is moved to matching area；
S102: judge whether the phrase phrase matching corresponding with matching area is correct；
If correct, then follow the steps S103: providing correct prompt,
If incorrect, then follow the steps S104 phrase and return to original position；
After the completion of all matchings, step S105 is executed, is scored after the completion of all matchings.
The embodiment of the invention also provides a kind of computer program products comprising instruction.When the computer program product exists
When being run on computer, so that the method that computer executes above-mentioned Fig. 4 and Fig. 5.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
The basic principle of the disclosure is described in conjunction with specific embodiments above, however, it is desirable to, it is noted that in the disclosure
The advantages of referring to, advantage, effect etc. are only exemplary rather than limitation, must not believe that these advantages, advantage, effect etc. are the disclosure
Each embodiment is prerequisite.In addition, detail disclosed above is merely to exemplary effect and the work being easy to understand
With, rather than limit, it is that must be realized using above-mentioned concrete details that above-mentioned details, which is not intended to limit the disclosure,.
Device involved in the disclosure, device, equipment, system block diagram only as illustrative example and being not intended to
It is required that or hint must be attached in such a way that box illustrates, arrange, configure.As those skilled in the art will appreciate that
, it can be connected by any way, arrange, configure these devices, device, equipment, system.Such as "include", "comprise", " tool
" etc. word be open vocabulary, refer to " including but not limited to ", and can be used interchangeably with it.Vocabulary used herein above
"or" and "and" refer to vocabulary "and/or", and can be used interchangeably with it, unless it is not such that context, which is explicitly indicated,.Here made
Vocabulary " such as " refers to phrase " such as, but not limited to ", and can be used interchangeably with it.
In addition, as used herein, the "or" instruction separation used in the enumerating of the item started with "at least one"
It enumerates, such as enumerating for " at least one of A, B or C " means A or B or C or AB or AC or BC or ABC (i.e. A and B and C).
In addition, wording " exemplary " does not mean that the example of description is preferred or more preferable than other examples.
It may also be noted that in the system and method for the disclosure, each component or each step are can to decompose and/or again
Combination nova.These decompose and/or reconfigure the equivalent scheme that should be regarded as the disclosure.
The technology instructed defined by the appended claims can not departed from and carried out to the various of technology described herein
Change, replace and changes.In addition, the scope of the claims of the disclosure is not limited to process described above, machine, manufacture, thing
Composition, means, method and the specific aspect of movement of part.Can use carried out to corresponding aspect described herein it is essentially identical
Function or realize essentially identical result there is currently or later to be developed processing, machine, manufacture, event group
At, means, method or movement.Thus, appended claims include such processing, machine, manufacture, event within its scope
Composition, means, method or movement.
The above description of disclosed aspect is provided so that any person skilled in the art can make or use this
It is open.Various modifications in terms of these are readily apparent to those skilled in the art, and are defined herein
General Principle can be applied to other aspect without departing from the scope of the present disclosure.Therefore, the disclosure is not intended to be limited to
Aspect shown in this, but according to principle disclosed herein and the consistent widest range of novel feature.
Claims (8)
1. a kind of artificial intelligence deep learning realize system characterized by comprising
Picture storage module, for store picture to be learned and with the one-to-one matching area of picture to be learned；
Phrase memory module, for storing phrase, the phrase includes phrase corresponding with the picture to be learned；
Correct matching memory module, the matching relationship including the matching area and the picture to be learned；
Mobile module, for the picture to be learned to be moved to the matching area；
Transmission unit, for the mobile data of the mobile module to be sent to server；
Server, the server include first judgment module, and the phrase for judging to be moved to the matching area is
It is no correct,
If correct, correct prompt is provided,
If incorrect, the phrase returns to original position.
2. artificial intelligence according to claim 1 deep learning realize system, which is characterized in that described one kind is artificial
Intelligently deep learning realizes system further include:
Grading module, for scoring after the matching area is matched with correct phrase.
3. artificial intelligence according to claim 2 deep learning realize system, which is characterized in that the grading module
The marking mode of use are as follows:
If the number that phrase returns to original position is 0, score is full marks, is denoted as M；
If phrase, which returns to original position number, is greater than 0, scored using formula (1):
Wherein,
M0- score；
N-matching times；
N0- matching area number；
M-full marks；
The number of the P-phrase that mistake is crossed in the past and this time mistake is crossed again；
The number of errors of the more difficult vocabulary of R-.
4. artificial intelligence according to claim 1 deep learning realize system, which is characterized in that described teaches a kind of people
Intelligently deep learning realizes system to work further include:
Second judgment module, for judging whether mobile number is greater than first threshold, if mobile number is greater than first threshold
Value, then terminate.
5. artificial intelligence according to claim 4 deep learning realize system, which is characterized in that the first threshold
It is 2 times of matching area number.
6. artificial intelligence according to claim 1 deep learning realize system, which is characterized in that the transmission unit
The mobile data of transmission is result data.
7. artificial intelligence according to claim 1 deep learning realize system, which is characterized in that the mobile module packet
Include screen shell (101), touch screen (102), penholder (110), stylus (120), the first guide rail (121), region ring (130), area
(200) are locked in domain, and the screen shell (101) is fixed with touch screen (102), and the two of the screen shell (101) and the penholder (110)
End is fixed, and the middle part of the penholder (110) offers first through hole (111) along its side, is equipped in the first through hole (111)
Stylus (120), the first through hole (111) are connected to one end of at least four first guide rails (121), and described at least four
The other end of one guide rail (121) and the region ring (130) are fixed, close first guide rail of the region ring (130)
(121) region lock (200) is equipped at, at least four region rings (130) are arranged respectively at touch screen (102) display at least
Four matching areas, the touch screen (102) at least four matching areas show different phrases, the first through hole respectively
(111) touch screen (102) at shows picture to be learned, and (200) are locked in the server and the touch screen (102), region
Power module connection, when the phrase of the matching area at region lock (200) is with the picture match to be learned, then server is beaten
(200) are locked in open region, when the phrase and the picture to be learned of the matching area at region lock (200) mismatch, are then serviced
Device closes region lock (200)；
Region lock (200) includes arc-shaped guide rail (201), the first electromagnet (202), arc ring (203), limited block (204),
The side surface of the arc-shaped guide rail (201) and the region ring (130) is fixed, and the region ring (130) is equipped with and described first
Second through-hole of guide rail (121) perforation, the side surface positioned at second through hole of the region ring (130) and the arc
Guide rail (201) is fixed, is set on the arc-shaped guide rail (201) there are two the first electromagnet (202) being moved along it, and two described the
The power module of one electromagnet (202) is connect with server, the separate arc-shaped guide rail of first electromagnet (202)
(201) surface of middle line is fixed with arc ring (203), and the both ends of the arc-shaped guide rail (201) are equipped with limited block (204).
8. a kind of artificial intelligence deep learning realize the implementation method of system, a kind of artificial intelligence deep learning it is real
Existing system be a kind of described in any item artificial intelligence of claim 1-7 deep learning realize system, the implementation method
Include the following steps:
Picture to be learned is moved to matching area；
Whether the judgement picture to be learned phrase matching corresponding with matching area is correct；
If correct, correct prompt is provided, if incorrect, picture to be learned returns to original position.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910432387.0A CN110111649B (en) | 2018-09-13 | 2018-09-13 | Artificial intelligence deep learning implementation system and method |
| CN201811068037.2A CN109345906B (en) | 2018-09-13 | 2018-09-13 | A kind of artificial intelligence deep learning realize system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811068037.2A CN109345906B (en) | 2018-09-13 | 2018-09-13 | A kind of artificial intelligence deep learning realize system and method |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910432387.0A Division CN110111649B (en) | 2018-09-13 | 2018-09-13 | Artificial intelligence deep learning implementation system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109345906A true CN109345906A (en) | 2019-02-15 |
| CN109345906B CN109345906B (en) | 2019-08-06 |
Family
ID=65305008
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811068037.2A Active CN109345906B (en) | 2018-09-13 | 2018-09-13 | A kind of artificial intelligence deep learning realize system and method |
| CN201910432387.0A Active CN110111649B (en) | 2018-09-13 | 2018-09-13 | Artificial intelligence deep learning implementation system and method |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910432387.0A Active CN110111649B (en) | 2018-09-13 | 2018-09-13 | Artificial intelligence deep learning implementation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN109345906B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110379216A (en) * | 2019-07-11 | 2019-10-25 | 宝云 | A kind of pupil langue leaning system in English |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120019318A (en) * | 2010-08-25 | 2012-03-06 | (주)컴퍼스미디어 | System and method for test of vocabulary size |
| CN102682629A (en) * | 2011-03-08 | 2012-09-19 | 汉王科技股份有限公司 | Line connection matching method and device for electronic whiteboard |
| CN204440686U (en) * | 2015-03-23 | 2015-07-01 | 马兆华 | A kind of novel decoding formula English teaching aid |
| CN106056991A (en) * | 2016-07-19 | 2016-10-26 | 北京乐学企鹅教育科技有限公司 | Early child education system and method based on Chinese character recognition |
| CN106710372A (en) * | 2017-01-11 | 2017-05-24 | 成都市极米科技有限公司 | Pinyin card identification method, device and terminal device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204480524U (en) * | 2015-03-31 | 2015-07-15 | 李延勤 | A kind of novel primary school Chinese phonetic training aid |
| CN205028477U (en) * | 2015-10-22 | 2016-02-10 | 哈尔滨师范大学 | English word teaching frame |
| CN206271198U (en) * | 2016-11-19 | 2017-06-20 | 曹海丽 | The data analysis displaying teaching aid that a kind of Teaching of Psychology is used |
| CN107067885A (en) * | 2017-05-27 | 2017-08-18 | 冯雪 | Presentation board for English teaching |
| CN209216310U (en) * | 2018-08-29 | 2019-08-06 | 倪凡 | A kind of extendible media teaching equipment based on text teaching |
-
2018
- 2018-09-13 CN CN201811068037.2A patent/CN109345906B/en active Active
- 2018-09-13 CN CN201910432387.0A patent/CN110111649B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120019318A (en) * | 2010-08-25 | 2012-03-06 | (주)컴퍼스미디어 | System and method for test of vocabulary size |
| CN102682629A (en) * | 2011-03-08 | 2012-09-19 | 汉王科技股份有限公司 | Line connection matching method and device for electronic whiteboard |
| CN204440686U (en) * | 2015-03-23 | 2015-07-01 | 马兆华 | A kind of novel decoding formula English teaching aid |
| CN106056991A (en) * | 2016-07-19 | 2016-10-26 | 北京乐学企鹅教育科技有限公司 | Early child education system and method based on Chinese character recognition |
| CN106710372A (en) * | 2017-01-11 | 2017-05-24 | 成都市极米科技有限公司 | Pinyin card identification method, device and terminal device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110379216A (en) * | 2019-07-11 | 2019-10-25 | 宝云 | A kind of pupil langue leaning system in English |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110111649B (en) | 2021-02-02 |
| CN109345906B (en) | 2019-08-06 |
| CN110111649A (en) | 2019-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gottlieb et al. | Academic language in diverse classrooms: Definitions and contexts | |
| Wallace et al. | Writing and learning in the science classroom | |
| Folse | Applying L2 lexical research findings in ESL teaching | |
| East | Foundational principles of task-based language teaching | |
| Hyland | Genre and second language writing | |
| Burke | Rituals and beliefs ingrained in world language pedagogy: Defining deep structure and conventional wisdom | |
| Mao | The Application of Task-based Language Teaching to English Reading Classroom. | |
| Rappa et al. | Integrating disciplinary-specific genre structure in discourse strategies to support disciplinary literacy | |
| CN109345906B (en) | A kind of artificial intelligence deep learning realize system and method | |
| Andrei et al. | Designing an American Sign Language avatar for learning computer science concepts for deaf or hard-of-hearing students and deaf interpreters | |
| Chia et al. | Re-defining ‘reading’in the 21st century: Accessing multimodal texts | |
| Ellis | What Happened to Teachers' Knowledge when they Played ‘The Literacy Game'? | |
| Wallace et al. | The role of language in science learning and literacy | |
| Cortazzi et al. | Conclusions: What are we learning from research about Chinese learners? | |
| Azizova et al. | Peculiarities Of Developing Discourse Competence In Writing | |
| CN207233258U (en) | A kind of economical management teaching display board | |
| CN203609037U (en) | Lawyer practice teaching material storage and inquiry device | |
| Ruifeng et al. | A Thorough Review of Pedagogical Content Knowledge (PCK) in TOBACCO framework | |
| Jordan et al. | Reformulating student contributions in tutorial dialogue | |
| Liu | Informatization of Constructive English Learning Platform Based on Improved GLR Algorithm | |
| McPherron | Internationalizing teaching, localizing English: Language teaching reforms through a south Chinese university | |
| Li et al. | Is ChatGPT a Good Middle School Teacher? An Exploration of its Role in Instructional Design | |
| Chen | RESEARCH ON THE CONSTRUCTION OF NEW MECHANISM OF TEACHING SYSTEM IN UNIVERSITIES BASED ON MASLOW'S HIERARCHY OF NEEDS | |
| Tan | The Application of Vocabulary Cohesion and Richness in College English Writing under the Flipped Classroom Model | |
| He | A Comparative Study of Multimodal Discourse in Grammar Teaching Between the Chinese Novice Teacher and the Experienced Teacher--Take Ba-Construction as an Example |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190705 Address after: Room 315, Room 33, Xiya Road, China (Shanghai) Free Trade Pilot Area, 2013 Applicant after: SHANGHAI XINDING NETWORK TECHNOLOGY Co.,Ltd. Address before: 100061 No. 1-3-402 Yingfang West Street, Dongcheng District, Beijing Applicant before: BEIJING LUOBIDA TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A deep learning implementation system and method based on artificial intelligence Effective date of registration: 20230509 Granted publication date: 20190806 Pledgee: Industrial Bank Co.,Ltd. Shanghai pilot Free Trade Zone Lingang New District sub branch Pledgor: SHANGHAI XINDING NETWORK TECHNOLOGY Co.,Ltd. Registration number: Y2023310000170 |