The patent application of the invention is divisional application. The patent number of the original case is 201811068037.2, the application date is 2018, 9 and 13, and the invention name is an artificial intelligence deep learning implementation system and method.
Disclosure of Invention
The embodiment of the invention aims to provide an artificial intelligence deep learning implementation system and method, and the artificial intelligence deep learning implementation system provided by the embodiment of the invention can realize automatic judgment of matching of phrases and pictures of students and improve the learning efficiency of the students.
The purpose of the embodiment of the invention is realized by the following technical scheme:
in a first aspect, an embodiment of the present invention provides an artificial intelligence deep learning implementation system, including:
the picture storage module is used for storing pictures to be learned and matching areas corresponding to the pictures to be learned one by one;
the phrase storage module is used for storing phrases, and the phrases comprise phrases corresponding to the pictures to be learned;
the correct matching storage module comprises a matching relation between the matching area and the phrase;
the moving module is used for moving the phrase to the matching area;
the sending unit is used for sending the mobile data of the mobile module to a server;
the server comprises a first judging module used for judging whether the phrase moved to the matching area is correct or not,
if the result is correct, a correct prompt is given,
if not, the phrase returns to the original position.
Further, the system for implementing artificial intelligence deep learning further comprises:
and the scoring module is used for scoring after the matching areas are matched with the correct phrases.
Further, the scoring module adopts a scoring mode that:
if the number of times of returning the phrase to the original position is 0, the score is full and is marked as M;
if the times of returning the phrase to the original position are more than 0, scoring by adopting a formula (1):
wherein the content of the first and second substances,
M0-a score;
n-matching times;
N0-number of matching regions;
m-full mark.
P is the number of the phrases which have been wrong before and are wrong at this time;
r is the number of errors of the difficult vocabulary.
Further, the system for implementing artificial intelligence deep learning further comprises:
and the second judging module is used for judging whether the moving times is greater than the first threshold value or not, and if the moving times is greater than the first threshold value, ending the process.
Further, the first threshold is 2 times of the number of the matching regions.
Further, the mobile data sent by the sending unit is result data.
In a second aspect, an embodiment of the present invention provides an implementation method of an artificial intelligence deep learning implementation system, where the artificial intelligence deep learning implementation system is any one of the above artificial intelligence deep learning implementation systems, and the implementation method includes the following steps:
moving the phrase to the matching area;
judging whether the matching of the phrase and the picture corresponding to the matching area is correct or not;
if the word group is correct, a correct prompt is given, and if the word group is incorrect, the word group returns to the original position.
By the scheme, the artificial intelligence deep learning implementation system at least has the following beneficial effects:
the system for realizing artificial intelligence deep learning comprises a first judging module, a second judging module, a third judging module, a fourth judging module, a fifth judging module and a sixth judging module.
The system score is scored according to the number of the matching times and the number of the pictures (matching areas), the number of the pictures is fully considered, and reasonable scoring is given.
This application has still set up the threshold value of matching the number of times, can prevent like this that the student from carrying out random matching to picture and phrase, and not study carefully, prevent the waste of teaching resource.
In the application, the sending unit only sends the result data, but not the process data, so that the pressure of the server is effectively reduced.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples, which should be understood as the technical solutions of the present invention are easier for those skilled in the art to understand, and should not be taken as a limitation of the scope of the present invention.
In the following description, the terms "first" and "second" are used for descriptive purposes only and are not intended to indicate or imply relative importance. The following description provides embodiments of the invention, which may be combined with or substituted for various embodiments, and the invention is thus to be construed as embracing all possible combinations of the same and/or different embodiments described. Thus, if one embodiment includes feature A, B, C and another embodiment includes feature B, D, then the invention should also be construed as including embodiments that include one or more of all other possible combinations of A, B, C, D, even though such embodiments may not be explicitly recited in the following text.
Fig. 1 is a schematic structural diagram of an artificial intelligence deep learning implementation system in an embodiment of the present invention, and as shown in fig. 1, the artificial intelligence deep learning implementation system in the embodiment of the present invention includes:
the picture storage module 101 is used for storing pictures to be learned and matching areas corresponding to the pictures to be learned one by one;
a phrase storage module 102, configured to store phrases, where the phrases include phrases corresponding to the to-be-learned picture;
the correct matching storage module 103 comprises a matching relation between the matching area and the picture to be learned;
a moving module 104, configured to move the picture to be learned to the matching area;
a sending unit 105, configured to send the mobile data of the mobile module to a server;
a server 106, which includes a first determining module for determining whether the picture to be learned moved to the matching area is correct,
if the result is correct, a correct prompt is given,
if not, the phrase returns to the original position.
According to the system for realizing artificial intelligence deep learning, after the first judgment module judges the matching result, the correct prompt or the original position of the picture is directly returned according to the judgment result, so that students can automatically learn according to the prompt of the system in learning.
Fig. 2 is a schematic structural diagram of an artificial intelligence deep learning implementation system in another embodiment of the present invention, and as shown in fig. 2, the artificial intelligence deep learning implementation system includes:
the picture storage module 101 is used for storing pictures to be learned and matching areas corresponding to the pictures to be learned one by one;
here, it is to be noted that: the embodiment of the invention does not specifically limit the types of pictures to be learned, so long as the needs of learning can be met, and pictures suitable for learning in the age group are preferably selected, such as simple pictures for learning of kindergarten babies, such as scenes, fruits, stationery, vehicles and the like.
A phrase storage module 102, configured to store phrases, where the phrases include phrases corresponding to the to-be-learned picture;
here, it is to be noted that: the embodiment of the invention does not specifically limit the type of the phrases, as long as the learning requirements can be met, in some embodiments of the invention, the phrases can be selected from Chinese, English, Japanese or German, and different languages are designed according to different learning requirements.
A correct matching storage module 103, which includes the matching relationship between the matching area and the phrase;
here, it is to be noted that: each matching area corresponds to one picture, the phrase corresponding to the picture is unique, and the server can judge the matching as long as the correct picture to be learned is moved to the matching area.
A moving module 104, configured to move the picture to be learned to the matching area;
a sending unit 105, configured to send the mobile data of the mobile module to a server;
a server 106, which includes a first determining module for determining whether the picture to be learned moved to the matching area is correct,
if the result is correct, a correct prompt is given,
if not, the phrase returns to the original position;
here, it is to be noted that: the method for giving the correct prompt is not limited in particular, and the prompt may be voice, such as "correct answer", "GOOD", "bar-stick" and the like, may be corresponding text, and may also play corresponding animation while playing voice, so as to improve the learning fun of students.
And the scoring module 107 is configured to score after the matching regions are matched with the correct pictures to be learned.
In some embodiments of the present invention, the scoring module adopts a scoring method that:
if the number of times of returning the phrase to the original position is 0, the score is full and is marked as M;
if the times of returning the phrase to the original position are more than 0, scoring by adopting a formula (1):
wherein the content of the first and second substances,
M0-a score;
n-matching times;
N0-number of matching regions;
m-full mark.
P is the number of the phrases which have been wrong before and are wrong at this time;
r is the number of errors of the difficult vocabulary.
The invention introduces the number P of the phrases which are wrong before and wrong at this time and the wrong number R of the difficult vocabulary in the traditional algorithm, so as to correct the final score by the corresponding weight of 20 percent and 10 percent, thereby truly reflecting the actual cognitive ability and learning ability of the user and more accurately reflecting the learning ability.
Since the pictures to be learned and the phrases are in one-to-one correspondence, the number P of the phrases which have been previously mistaken and have been mistaken this time, that is, the number P of the pictures to be learned which have been previously mistaken and have been mistaken this time, similarly, the number R of the errors of the vocabulary which are difficult, that is, the number of the errors of the pictures to be learned which are difficult.
Wherein, for example, the full score M is 100, the matching times N is 100, and the number of matching regions N is082 times, that is, the number of times of returning the phrase to the original position is 18 times, the number P of the previously wrong phrases which are wrong again this time is 2, the number R of errors of the difficult vocabulary is 2, and then the score M is given0Is 85.608. Compared with the score of 82 in the traditional algorithm, the method has better referential performance, is helpful for teachers to know the learning conditions of children, and ranks students more reasonably.
The difficult vocabulary may be a gap vocabulary, for example, the user is a schoolchild, and the vocabulary outside the kindergarten outline in the elementary school outline may be a difficult vocabulary, and for example, the user is a junior student, and the vocabulary outside the elementary school outline in the junior outline may be a difficult vocabulary. When the user mistakenly has more difficult vocabularies, the score of the user can be correspondingly and minutely improved so as to embody the weight of the difficult vocabularies, facilitate the ranking of students and enable teachers to observe the learning conditions of the students according to the score of the user.
The previously and this time wrong phrases may be repeated wrong words, for example, the wrong phrase stored in the database by the server is compared with the existing phrase returned to the original position, and if the phrase matches, the number of the match is counted as P.
Here, it is to be noted that: the artificial intelligence deep learning implementation system score is scored according to the matching times and the number of the pictures (matching regions), the number of the pictures is fully considered, and reasonable scores are given.
Fig. 3 is a schematic structural diagram of an artificial intelligence deep learning implementation system in another embodiment of the present invention, as shown in fig. 3, the artificial intelligence deep learning implementation system further includes:
the second determining module 108 is configured to determine whether the moving frequency is greater than a first threshold, and if the moving frequency is greater than the first threshold, the process is ended.
In some embodiments of the present invention, the first threshold is 2 times the number of matching regions.
Here, it is to be noted that: the artificial intelligence deep learning implementation system provided by the embodiment of the invention sets the threshold value of the matching times, so that the random matching of pictures and phrases by students can be prevented, the pictures and phrases are not carefully learned, and the waste of teaching resources is prevented.
In some embodiments of the present invention, the mobile data transmitted by the transmitting unit is result data.
Here, it is to be noted that: the sending unit 105 in the embodiment of the present invention only sends the result data, but does not send the process data, such as data of a moving route, a moving speed, and the like of a phrase during the moving of the phrase by a student, and the sending unit does not send a related operation process to the server, but only sends the result data, such as a position, a moving frequency, and the like of a final picture, so that the pressure of the server can be effectively reduced, and resources can be saved.
Preferably, as shown in fig. 6 to 12, referring to fig. 6, 8, 9, and 11, the mobile module includes a screen shell 101, a touch screen 102, a pen holder 110, a stylus 120, a first guide rail 121, a region ring 130, and a region lock 200, the touch screen 102 is fixed on the screen shell 101, the screen shell 101 is fixed to both ends of the pen holder 110, a first through hole 111 is formed in the middle of the pen holder 110 along a side surface thereof, the stylus 120 is disposed in the first through hole 111, the first through hole 111 is communicated with one end of at least four first guide rails 121, the other end of the at least four first guide rails 121 is fixed to the region ring 130, the region lock 200 is disposed on the region ring 130 near the first guide rail 121, the at least four region rings 130 are respectively disposed in at least four matching regions displayed on the touch screen 102, the touch screens 102 in the at least four matching regions respectively display different phrases, the touch screen 102 at the first through hole 111 displays a picture to be learned, the server is connected with the touch screen 102 and a power module of the area lock 200, when a phrase of a matching area at the area lock 200 is matched with the picture to be learned, the server opens the area lock 200, and when the phrase of the matching area at the area lock 200 is not matched with the picture to be learned, the server closes the area lock 200;
referring to fig. 9 and 10, the area lock 200 includes an arc guide rail 201, first electromagnets 202, an arc ring 203, and limiting blocks 204, the arc guide rail 201 is fixed to a side surface of the area ring 130, the area ring 130 is provided with a second through hole penetrating the first guide rail 121, a side surface of the area ring 130 located at the second through hole is fixed to the arc guide rail 201, the arc guide rail 201 is provided with two first electromagnets 202 moving along the arc guide rail, power modules of the two first electromagnets 202 are connected to a server, the surface of the first electromagnet 202 away from a center line of the arc guide rail 201 is fixed to the arc ring 203, and the two ends of the arc guide rail 201 are provided with the limiting blocks 204.
The pen rack 110, the first guide rail 121 and the area ring 130 can standardize the track of the user sliding the touch screen 102, and the area lock 200 can more intuitively enable the user, especially the user in primary schools, kindergartens and the following schools, to have more intuitive feeling for correct and incorrect matching, thereby helping the user to more conveniently learn pictures and phrases deeply.
The limiting block 204 can be made of plastic, iron, aluminum or resin, of course, the limiting block 204 can also be made of a permanent magnet, so that when the regional lock 200 is controlled to be closed by the server, the first electromagnets 202 are directly powered off after being mutually repelled, the limiting block 204 made of the permanent magnet continuously attracts the first electromagnets 202, and the regional lock 200 can be in a closed state when the first electromagnets 202 are not powered on, so that power is saved.
The arc-shaped ring 203 and the arc-shaped guide rail 201 are coaxially arranged, and the arc length occupied by the arc-shaped ring 203 and the first electromagnet 202 is preferably 3/16 to 1/4 circumferences, such circumferences can prevent the stylus 120 from entering the matching area when the area lock 200 is closed, that is, the server controls the two first electromagnets 202 to repel, and can move the stylus to the matching area when the area lock 200 is opened, that is, the server controls the two first electromagnets 202 to attract each other, and the stylus 120 can still be moved to the matching area by the driving force of the stylus 120 when the two mutually attracted first electromagnets 202 are not located at the center line of the arc-shaped guide rail 201.
At least one end of the arc-shaped guide rail 201 is fixed to the side surface of the area ring 130 at the second through hole, or both ends of the arc-shaped guide rail may be fixed thereto. Thereby ensuring that the arc-shaped guide rail 201 is circular towards said first guide rail 121.
The second through hole formed in the area ring 130 and penetrating through the first guide rail 121 enables the stylus 120 to move into the area ring 130, or at least half of the stylus 120 moves into the area ring 130, and ensures that the stylus 120 can smoothly slide back to the first guide rail 121.
The user slides the picture to be learned to the matching area through the stylus 120, if the picture is matched, the user can intuitively drag the stylus 120 into the area lock 200, and if the picture is not matched, the area lock 200 rejects the stylus 120, or the area lock 200 prevents the stylus 120 from moving to the matching area;
the stylus pen 120 can move from the first through hole 111 to the area lock 200 through the first guide rail 121, and can always touch and slide with the touch screen 102 during the movement. The first through hole 111 may also penetrate through the side surface of the pen holder 110, that is, it may be understood that the side surface of the pen holder 110 is provided with a guide groove identical to the first through hole 111, the guide groove is connected to the first guide rail 121, the first guide rail 121 may be made of two rods or plates which are arranged left and right and are parallel to each other, and the at least four first guide rails 121 may be fixed to the pen holder 110 at different axial positions of the first guide rails 121, so that a user may slide out the stylus from any one of the at least four first guide rails 121.
In a second aspect, an embodiment of the present invention provides an implementation method of an artificial intelligence deep learning implementation system, where the artificial intelligence deep learning implementation system is any one of the above artificial intelligence deep learning implementation systems, and fig. 4 is a flowchart of an implementation method of an artificial intelligence deep learning implementation system in an embodiment of the present invention, and as shown in fig. 4, the implementation method includes the following steps:
s101, moving a picture to be learned to a matching area;
s102, judging whether the matching between the picture to be learned and the corresponding phrase of the matching area is correct or not;
if it is correct, execute step S103: the correct prompt is given and the correct prompt is given,
if not, executing step S104 to return the phrase to the original position.
Fig. 5 is a flowchart of an implementation method of an artificial intelligence deep learning implementation system in another embodiment of the present invention, as shown in fig. 5, the implementation method includes the following steps:
s101, moving a picture to be learned to a matching area;
s102, judging whether the matching of the phrase and the phrase corresponding to the matching area is correct or not;
if it is correct, execute step S103: the correct prompt is given and the correct prompt is given,
if not, executing step S104 to return the phrase to the original position;
after all the matches are completed, step S105 is executed, and after all the matches are completed, scoring is performed.
The embodiment of the invention also provides a computer program product containing the instruction. Which when run on a computer causes the computer to perform the methods of fig. 4 and 5 described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
Also, as used herein, the use of "or" in a list of items beginning with "at least one" indicates a separate list, e.g., "A, B or at least one of C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the described example is preferred or better than other examples.
It is also noted that in the systems and methods of the present disclosure, components or steps may be decomposed and/or re-combined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
Various changes, substitutions and alterations to the techniques described herein may be made without departing from the techniques of the teachings as defined by the appended claims. Moreover, the scope of the claims of the present disclosure is not limited to the particular aspects of the process, machine, manufacture, composition of matter, means, methods and acts described above. Processes, machines, manufacture, compositions of matter, means, methods, or acts, presently existing or later to be developed that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein may be utilized. Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or acts.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.