CN111881895A

CN111881895A - AI intelligent question-cutting method and device for wrong questions of operation

Info

Publication number: CN111881895A
Application number: CN202010960557.5A
Authority: CN
Inventors: 杨润平
Original assignee: Shenzhen Shiyueyi Technology Co ltd
Current assignee: Shenzhen Shiyueyi Technology Co ltd
Priority date: 2020-09-14
Filing date: 2020-09-14
Publication date: 2020-11-03

Abstract

The invention provides an AI intelligent question-cutting method and device for operation wrong questions, wherein the method comprises a wrong question-cutting process, the wrong question-cutting process comprises the steps of obtaining corrected operation data, and the operation data comprises pictures, Word, PDF and Excel formats; converting the modified job data in the non-picture format into job data in the picture format; denoising, distortion correction and binarization processing are carried out on the operation data in the picture format; identifying error questions through an AI intelligent question-cutting system from the operation data in the picture format; and intercepting the error questions from the operation data in the picture format to form an error question book. The invention has the beneficial effects that: by the method, the student homework wrong questions are automatically recognized, the students do not need to manually mark the wrong questions, and teachers can more conveniently and quickly master the homework conditions of the students.

Description

AI intelligent question-cutting method and device for wrong questions of operation

Technical Field

The present invention relates to a method and an apparatus for automatically cutting off questions, and more particularly, to a method and an apparatus for automatically cutting off AI questions that are wrong in work.

Background

The prior homework management system does not form wrong question books on the correction results of the out-of-class homework, and is not convenient for students to redo wrong questions; moreover, an electronic file is not formed after the paper work is corrected, so that the paper work is inconvenient to check in real time; moreover, for paper work, teachers are inconvenient to manage the number of wrong questions, and lack of targeted wrong question explanation and wrong question analysis.

Therefore, the existing homework management method needs to be improved, so that wrong questions of paper homework can form wrong question books quickly, and teachers can master the homework condition of each student quickly.

Disclosure of Invention

The technical problem to be solved by the invention is as follows: an AI intelligent question-cutting method and device for homework wrong questions are provided, which aim to automatically identify the student homework wrong questions and form wrong question books.

In order to solve the technical problems, the invention adopts the technical scheme that: an AI intelligent question-cutting method for operation wrong questions comprises a wrong question-cutting process, which comprises the following steps,

s21, acquiring the corrected job data, wherein the job data comprises pictures, Word, PDF and Excel formats;

s22, converting the corrected job data in the non-picture format into the job data in the picture format;

s23, denoising, distortion correcting and binaryzing the operation data in the picture format;

s24, identifying error questions from the operation data in the picture format through an AI intelligent question-cutting system;

and S25, cutting the error question from the operation data in the picture format to form an error question book.

Furthermore, the AI intelligent topic cutting method for wrong tasks also comprises a topic cutting model training process, which comprises the following steps,

s11, calculating error questions through an algorithm by the error question model, comparing the error questions with the manually acquired error questions, and continuously training an enriched error question library to obtain an intelligent acquisition error question model;

s12, the question model manually collects question models, trains operation question types according to different subjects, and calculates the rule of question number composition to obtain an intelligent question model;

s13, training the correct and wrong line tracks of the correction operation by the behavior model to obtain an intelligent acquisition wrong behavior model;

and S14, combining an AI algorithm, and realizing AI learning training through a training model library to obtain an item type item number feature library, a wrong item feature library and a behavior feature library.

Further, step S12 specifically includes,

the question type training, the question type question number model compares the question number of the trained question with the question number of the manually collected question type according to different subjects, and covers various question type operations of different subjects through the question type training;

and (4) question number training, which is to train the composition rule of question numbers by combining the question characteristics of each subject operation.

Further, step S13 specifically includes,

track training, namely comparing the line tracks with correct and wrong operation correction with a manually-acquired wrong behavior model, and improving the threshold values of the correct and wrong tracks;

performing comprehensive training on wrong questions, and training the color of the corrected font;

and (4) behavior habit training, namely assisting in homework segmentation according to the behavior habits of students for correcting homework.

Furthermore, the AI intelligent question-cutting method for operation wrong questions also comprises a wrong question management process which comprises,

s31, respectively counting the wrong questions according to the users, the disciplines and the knowledge points so as to classify and summarize the wrong questions;

and S32, generating an error question file according to the error question template for the student to export or print the error question.

The invention also provides an AI intelligent question-cutting device for operation wrong questions, which comprises a wrong question-cutting module,

the data acquisition unit is used for acquiring the corrected job data, and the job data comprises pictures, Word, PDF and Excel formats;

the format conversion unit is used for converting the homework data in the non-picture format after the approval into the homework data in the picture format;

the preprocessing unit is used for denoising, distortion correction and binarization processing on the operation data in the picture format;

the error question identification unit is used for identifying error questions from the operation data in the picture format through an AI intelligent question-cutting system;

and the wrong question intercepting unit is used for intercepting the wrong questions from the operation data in the picture format to form a wrong question book.

Furthermore, the AI intelligent question cutting device for wrong work questions also comprises a question cutting model training module which comprises,

the first model training unit is used for calculating the error questions through an algorithm by the error question model, comparing the error questions with the manually acquired error questions, and continuously training and enriching an error question library to obtain an intelligent acquisition error question model;

the second model training unit is used for the question model to manually collect question models, train operation question types according to different subjects, calculate the rule of question number composition and obtain an intelligent question model;

the third model training unit is used for training the correct and wrong line tracks of the correction operation by the behavior model to obtain an intelligent acquisition wrong-question behavior model;

and the model base training unit is used for realizing AI learning training by combining an AI algorithm and training the model base to obtain a question type question number feature base, a wrong question feature base and a behavior feature base.

Further, the second model training unit is specifically configured to,

Further, the third model training unit is specifically configured to,

Furthermore, the AI intelligent title device for operation wrong titles also comprises a wrong title management module, the wrong title management module comprises,

the wrong question counting unit is used for respectively counting the wrong questions according to the users, the disciplines and the knowledge points so as to classify and summarize the wrong questions;

and the wrong question exporting unit is used for generating a wrong question file according to the wrong question template so as to be exported or printed by students.

The invention has the beneficial effects that: firstly, the corrected operation data is obtained, the data in the non-picture format is converted into the picture format, so that the data is unified, and the subsequent processing of the data is facilitated; the image processing method comprises the steps of denoising, distortion correction and binarization processing of operation data in an image format, enabling an image to be clearer, greatly reducing data volume in the image, enabling the outline of an image target to be highlighted, identifying a wrong question through an AI (intelligent object-cutting) system, and intercepting the wrong question to form a wrong question book. By the method, the student homework wrong questions are automatically recognized, the students do not need to manually mark the wrong questions, and teachers can more conveniently and quickly master the homework conditions of the students.

Drawings

The following detailed description of the invention refers to the accompanying drawings.

FIG. 1 is a flow chart of training a topic model according to an embodiment of the present invention;

FIG. 2 is a flow chart of the problem solving process according to the embodiment of the present invention;

FIG. 3 is a flow chart of the problem management according to the embodiment of the present invention;

FIG. 4 is a block diagram of a topic model training module according to an embodiment of the present invention;

FIG. 5 is a block diagram of the problem solving module of the embodiment of the present invention;

FIG. 6 is a block diagram of a fault management system according to an embodiment of the present invention;

FIG. 7 is a diagram of an AI intelligent topic-cutting system in accordance with an embodiment of the present invention;

FIG. 8 is a schematic block diagram of a computer apparatus of an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

The first embodiment of the invention is as follows: an AI intelligent question-cutting method for operation wrong questions comprises a question-cutting model training process, a wrong question-cutting process and a wrong question management process;

wherein, as shown in FIG. 1, the training process of the topic model comprises the steps of,

Wherein, as shown in FIG. 2, the wrong topic cutting process includes steps,

in the step, by calling the API of the AI learning training part, the problems are identified, the problem stem is identified, the position information is obtained, the wrong problem behavior is judged and the problem number is compiled, so that the wrong problem is cut.

Wherein, as shown in FIG. 3, the error management process comprises steps,

In one embodiment, step S12 specifically includes,

In one embodiment, step S13 specifically includes,

track training, namely comparing the line tracks with correct and wrong operation correction with a manually-acquired wrong behavior model, and improving the threshold values of the correct and wrong tracks; wherein, the correction track of the teacher is √ and ×.

Performing error comprehensive training, training the corrected font color of the operation, wherein the training is binary training;

and (4) behavior habit training, which is used for assisting homework segmentation according to the behavior habits of students for correcting homework and improving the accuracy of homework segmentation.

As shown in fig. 7, the AI intelligent topic-cutting system used in this embodiment includes three parts, namely a training model library, an AI learning training and an intelligent processing, where the training model library includes a wrong topic model, a topic model and a behavior model, and the training of the model is realized through steps S11-S14.

The beneficial effect of this embodiment lies in: firstly, the corrected job data is obtained, and the data in the non-picture format is converted into the picture format, so that the data is unified, and the subsequent processing of the data is facilitated; the image processing method comprises the steps of denoising, distortion correction and binarization processing of operation data in an image format, enabling an image to be clearer, greatly reducing data volume in the image, enabling the outline of an image target to be highlighted, identifying a wrong question through an AI (intelligent object-cutting) system, and intercepting the wrong question to form a wrong question book.

The AI intelligent question-cutting system can automatically identify the student homework wrong questions without manually identifying the wrong questions by the students, so that teachers can more conveniently and quickly master the homework conditions of the students;

more intelligent, the homework correction condition of all students is detected in real time, and wrong questions are accurately identified, segmented, combined and summarized;

the method is more convenient and can check, export and print wrong questions at any time and any place.

The invention also provides an AI intelligent question-cutting device for operation wrong questions, which comprises a question-cutting model training module, a wrong question-cutting module and a wrong question management module,

wherein, as shown in FIG. 4, the topic model training module comprises,

the first model training unit 11 is used for calculating error questions through an algorithm by the error question model, comparing the error questions with the manually acquired error questions, and continuously training and enriching an error question library to obtain an intelligent acquisition error question model;

the second model training unit 12 is used for the question model to manually collect question models, train operation question types according to different subjects, calculate the rule of question number composition and obtain an intelligent question model;

the third model training unit 13 is used for training the correct and wrong line tracks of the correction operation by the behavior model to obtain an intelligent acquisition wrong-question behavior model;

and the model base training unit 14 is used for realizing AI learning training by training the model base in combination with an AI algorithm to obtain a question type question number feature base, a wrong question feature base and a behavior feature base.

Wherein, as shown in FIG. 5, the wrong topic module comprises,

the data acquisition unit 21 is configured to acquire the modified job data, where the job data includes a picture, a Word, a PDF, and an Excel format;

a format conversion unit 22 for converting the modified job data in the non-picture format into job data in the picture format;

the preprocessing unit 23 is configured to perform denoising, distortion correction, and binarization processing on the job data in the picture format;

the error question identification unit 24 is used for identifying error questions from the operation data in the picture format through an AI intelligent question-cutting system;

and an error question intercepting unit 25, configured to intercept an error question from the job data in the picture format to form an error question book.

As shown in fig. 6, the error question management module includes,

the wrong question counting unit 31 is used for respectively counting the wrong questions according to the users, the disciplines and the knowledge points so as to classify and summarize the wrong questions;

and the wrong question exporting unit 32 is used for generating a wrong question file according to the wrong question template, so that students can export or print the wrong question book.

In a specific embodiment, the second model training unit 12 is specifically configured to,

In a specific embodiment, the third model training unit 13 is specifically configured to,

It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation processes of each module and each unit of the AI intelligent topic cutting device for the task error may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.

The AI intelligent topic cutting device for the task error can be implemented in a form of a computer program, and the computer program can be run on a computer device as shown in fig. 8.

Referring to fig. 8, fig. 8 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a terminal or a server, where the terminal may be an electronic device with a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of a plurality of servers.

Referring to fig. 8, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.

The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer programs 5032 include program instructions that, when executed, cause the processor 502 to perform an AI intelligent topic-cutting method for task errors.

The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.

The memory 504 provides an environment for the computer program 5032 in the non-volatile storage medium 503 to run, and when the computer program 5032 is executed by the processor 502, the processor 502 can be caused to execute an AI intelligent topic-cutting method for the task error.

The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 8 is a block diagram of only a portion of the configuration relevant to the present teachings and does not constitute a limitation on the computer device 500 to which the present teachings may be applied, and that a particular computer device 500 may include more or less components than those shown, or combine certain components, or have a different arrangement of components.

The processor 502 is configured to run the computer program 5032 stored in the memory to implement the AI intelligent topic-cutting method for the task error as described above.

It should be understood that, in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.

Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program comprises program instructions. The program instructions, when executed by the processor, cause the processor to perform the AI intelligent topic-cutting method for task faults as described above.

The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.

The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.

While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An AI intelligent question-cutting method for wrong questions of operation is characterized in that: comprises a wrong question cutting process, which comprises the following steps,

2. The AI intelligent question switching method for task malpractice according to claim 1, characterized in that: also comprises a training process of the topic cutting model, which comprises the following steps,

3. The AI intelligent question switching method for task malpractice according to claim 2, characterized in that: the step S12 specifically includes the steps of,

4. The AI intelligent question switching method for task malpractice according to claim 2, characterized in that: the step S13 specifically includes the steps of,

5. The AI intelligent question switching method for task malpractice according to claim 2, characterized in that: also comprises a wrong question management process which comprises,

6. The utility model provides a AI intelligence device of cutting questions of operation mistake which characterized in that: comprises a wrong question cutting module, the wrong question cutting module comprises,

7. The AI intelligent topic cutting device of task errors of claim 6, wherein: also comprises a model training module for the questions, the model training module for the questions comprises,

8. The AI intelligent topic cutting device of task errors of claim 7 wherein: the second model training unit is in particular adapted to,

9. The AI intelligent topic cutting device of task errors of claim 7 wherein: the third model training unit is specifically configured to,

10. The AI intelligent topic cutting device of task errors of claim 7 wherein: also comprises an error management module which comprises,