An online learning diagnosis method and device based on artificial intelligence

Abstract

The present invention discloses an online learning diagnosis method and device based on artificial intelligence. The online learning diagnosis method collects data of student test papers and homeworks as a first training set through OCR technology, and obtains a first neural network model through training; uses the test paper or homework, the corresponding total scores of each knowledge point, and teaching suggestions as a second training set, and obtains a second neural network model through training; obtains the answer content of the test paper or homework to be analyzed through the handwriting of an electronic pen, and inputs the first neural network model in combination with the test paper or homework to be analyzed to obtain the total scores of each knowledge point corresponding to the test paper or homework to be analyzed; inputs the total scores of each knowledge point corresponding to the test paper or homework to be analyzed into the second neural network model to obtain the teaching suggestions for the test paper or homework to be analyzed; the real mastery of each knowledge point by the students can be quickly and accurately evaluated, and appropriate teaching suggestions can be given, which not only saves the time and energy of teachers, but also helps students to quickly check for omissions and improve their grades.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an online learning diagnosis method and device based on artificial intelligence. Background Art

[0002] At present, the development of computer and Internet technology has promoted the rapid development of online learning. In real teaching, teachers still need to subjectively judge each student's weak knowledge points based on different students' homework completion scores and teaching experience, and then implement different teaching strategies for different students.

[0003] However, this process not only consumes a lot of teachers' time and energy, but also makes it difficult to accurately evaluate students' true mastery of each knowledge point based on the completion of a single assignment, and thus it is impossible to accurately give appropriate teaching suggestions. Summary of the invention

[0004] The main purpose of the present invention is to provide an online learning diagnosis method and device based on artificial intelligence, aiming to solve the problem in related technologies that it is difficult to accurately evaluate students' true mastery of each knowledge point and it is impossible to accurately give appropriate teaching suggestions.

[0005] In a first aspect, the present invention provides an online learning diagnosis method based on artificial intelligence, and the online learning diagnosis method based on artificial intelligence comprises the following steps:

[0006] The data of student test papers and homework are collected as a first training set by using OCR technology, and a first neural network model is obtained by training; the data of the student history test papers and homework include a plurality of questions, knowledge points corresponding to each question, and the answer content of each question; and also include the total score of each knowledge point of each test paper or homework;

[0007] The test papers or homework, the corresponding total scores of each knowledge point, and the teaching suggestions are used as the second training set to train a second neural network model;

[0008] The answer content of the test paper or homework to be analyzed is obtained through the handwriting of the electronic pen, and the answer content is input into the first neural network model in combination with the test paper or homework to be analyzed to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed;

[0009] The total scores of each knowledge point corresponding to the test paper or homework to be analyzed are input into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed.

[0010] Optionally, obtaining the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen specifically includes:

[0011] Collect the stroke order information and position information of the electronic pen to form different strokes;

[0012] The input characters are obtained according to the stroke combination to obtain the answer content; the characters include words, numbers, English or symbols.

[0013] Optionally, the data of student test papers and homeworks collected by OCR technology specifically includes:

[0014] Divide the paper test paper or homework into multiple modular areas according to different topics, and set the main coordinate axis, identification line and identification mark; each modular area has one topic;

[0015] Collecting the written content of each modular area, and identifying the content area according to the main coordinate axis, identification line and identification mark;

[0016] Use OCR technology to automatically identify and judge questions and answers;

[0017] The knowledge points included in the question are determined according to the question, and the total score of each knowledge point is obtained according to the answer content, and converted into an electronic format.

[0018] Optionally, after obtaining the total score of each knowledge point corresponding to the test paper or homework to be analyzed, the method further includes:

[0019] Calculate the total score of a test paper or homework;

[0020] The excellent rate, passing rate and average score are obtained based on the total scores of all students in the assessment, and the assessment entity is a class or grade.

[0021] Optionally, the online learning diagnosis method further includes:

[0022] According to the test papers or homeworks to be analyzed, the answer contents of the test papers or homeworks to be analyzed, and the corresponding total scores of each knowledge point, the first training set is updated to further train the first neural network model.

[0023] Optionally, the online learning diagnosis method further includes:

[0024] According to the total scores of each knowledge point corresponding to the test paper or homework to be analyzed, and the teaching suggestions for the test paper or homework to be analyzed, the second training set is updated to further train the second neural network model.

[0025] In a second aspect, in order to achieve the above-mentioned purpose, the present invention further proposes an online learning diagnosis device based on artificial intelligence, and the online learning diagnosis device based on artificial intelligence comprises:

[0026] A first acquisition module is used to collect data of student test papers and homework as a first training set through OCR technology; the data of the student history test papers and homework each includes a plurality of questions, a knowledge point corresponding to each question, and the answer content of each question; and also includes the total score of each knowledge point of each test paper or homework;

[0027] The first neural network model is trained by the first training set, and is used to input the test paper or homework to be analyzed, and obtain the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, and output the total score of each knowledge point corresponding to the test paper or homework to be analyzed;

[0028] A second acquisition module is used to acquire the test paper or homework, the corresponding total score of each knowledge point, and the teaching suggestions as the second training set;

[0029] The second neural network model is trained by the second training set, and is used to input the total scores of each knowledge point corresponding to the test paper or homework to be analyzed, and output teaching suggestions for the test paper or homework to be analyzed.

[0030] Optionally, the online learning diagnosis device further includes:

[0031] A storage module is used to store the student ID, all test papers or homework completed by the student ID and the corresponding total scores of each knowledge point, and all teaching suggestions;

[0032] The integration module is used to integrate all the test papers or homeworks completed by the student ID within the time period and the corresponding total scores of each knowledge point, as well as all teaching suggestions at regular intervals, to obtain the knowledge points and the corresponding total scores, and to sort the total scores of each knowledge point.

[0033] Optionally, the first acquisition module is specifically used to collect the stroke order information and position information of the electronic pen to form different strokes; and obtain input characters according to the stroke combination to obtain the answer content; the characters include text, numbers, English or symbols.

[0034] Optionally, the online learning diagnosis device further includes:

[0035] A comparison module is used to calculate the total score of a test paper or homework, and obtain the excellent rate, pass rate and average score based on the total score of all students in the assessment, where the assessment is for a class or grade;

[0036] The comparison module is also used to obtain the score track based on the total score of each test paper or homework, and calculate the student's ranking, progress or regression.

[0037] The artificial intelligence-based online learning diagnosis device method and apparatus proposed in the present invention obtain the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, combine the test paper or homework to be analyzed and input the first neural network model to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed, and then input the total score of each knowledge point corresponding to the test paper or homework to be analyzed into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed. It can quickly and accurately evaluate the students' true mastery of each knowledge point and give appropriate teaching suggestions, which not only saves teachers' time and energy, but also helps students quickly find omissions and improve their grades. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present invention;

[0039] Figure 2 This is a flow chart of a first embodiment of an online learning diagnosis method based on artificial intelligence of the present invention;

[0040] Figure 3 This is a flow chart of a second embodiment of an online learning diagnosis method based on artificial intelligence according to the present invention;

[0041] Figure 4 This is a flow chart of a third embodiment of an online learning diagnosis method based on artificial intelligence of the present invention;

[0042] Figure 5 This is a flow chart of a fourth embodiment of an online learning diagnosis method based on artificial intelligence of the present invention;

[0043] Figure 6 This is a functional module diagram of the first embodiment of the online learning diagnosis device based on artificial intelligence of the present invention;

[0044] Figure 7 This is a functional module diagram of the second embodiment of the online learning diagnosis device based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0046] The embodiments of the present application provide an artificial intelligence-based online learning diagnosis method and device, which can solve the problems in related technologies that it is difficult to accurately evaluate students' true mastery of each knowledge point and it is impossible to accurately give appropriate teaching suggestions.

[0047] The solution of the embodiment of the present invention is mainly as follows: using OCR technology to collect data of student test papers and homework as a first training set, and training to obtain a first neural network model; the data of the above-mentioned student history test papers and homework all include multiple questions, knowledge points corresponding to each question, and the answer content of each question; the data of the student history test papers and homework also include the total score of each knowledge point of each test paper or homework; using the test paper or homework, the corresponding total score of each knowledge point, and teaching suggestions as a second training set, training to obtain a second neural network model; obtaining the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, combining the test paper or homework to be analyzed and inputting it into the first neural network model, obtaining the total score of each knowledge point corresponding to the test paper or homework to be analyzed; inputting the total score of each knowledge point corresponding to the test paper or homework to be analyzed into the second neural network model, obtaining the teaching suggestions of the test paper or homework to be analyzed, so as to quickly and accurately evaluate the students' true mastery of each knowledge point, and give appropriate teaching suggestions, which not only saves teachers' time and energy, but also helps students quickly find out the gaps and improve their grades.

[0048] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present invention.

[0049] like Figure 1 As shown, the computer device includes a memory 101 , a processor 102 , and a computer program stored in the memory 101 and executable on the processor 102 .

[0050] Optionally, the processor 102 may be a CPU (Central Processing Unit), and the memory 101 may be a high-speed RAM (random access memory), or a storage device independent of the processor 102 .

[0051] In this embodiment, the computer device further includes a communication bus 103, a user interface 104 and a network interface 105. The communication bus 103 is used to realize the connection and communication between the above components. The user interface 104 may include but is not limited to a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. Optionally, the network interface 105 may include a standard wired interface, a wireless interface, etc.

[0052] Those skilled in the art will understand that Figure 1 The computer device structure shown in the figure does not constitute a limitation on the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0053] like Figure 1 As shown, the above-mentioned memory 1005 may include an operating system, a network communication module, a user interface module, and an online learning diagnostic program based on artificial intelligence.

[0054] The computer device of the present invention calls the artificial intelligence-based online learning diagnostic program stored in the memory 101 through the processor 102, and performs the following operations:

[0055] The data of student test papers and homeworks are collected through OCR technology as the first training set, and the first neural network model is trained; the data of the above-mentioned student history test papers and homeworks include multiple questions, the knowledge points corresponding to each question, and the answer content of each question; the data of student history test papers and homeworks also include the total score of each knowledge point of each test paper or homework.

[0056] The test papers or homework, the corresponding total scores of each knowledge point, and the teaching suggestions are used as the second training set to train a second neural network model.

[0057] The answer content of the test paper or homework to be analyzed is obtained through the handwriting of the electronic pen, and the test paper or homework to be analyzed is input into the first neural network model to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed. Among them, the knowledge points of the test paper or homework are fixed, that is, the knowledge point corresponding to each question can be obtained according to the test paper or homework to be analyzed.

[0058] The total scores of each knowledge point corresponding to the test paper or homework to be analyzed are input into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed.

[0059] The computer device of the present invention calls the artificial intelligence-based online learning diagnostic program stored in the memory 101 through the processor 102, and further performs the following operations:

[0060] Furthermore, when the processor executes the computer program, the processor also implements the following operations:

[0061] Collect the stroke order information and position information of the electronic pen to form different strokes;

[0062] The input characters are obtained according to the stroke combination to obtain the answer content; the above characters include words, numbers, English or symbols.

[0063] The computer device of the present invention calls the artificial intelligence-based online learning diagnostic program stored in the memory 101 through the processor 102, and further performs the following operations:

[0064] Divide the paper test paper or homework into multiple modular areas according to different topics, and set the main coordinate axis, identification line and identification mark; each modular area has one topic;

[0065] Collect the written content of each modular area, and identify the content area according to the above-mentioned main coordinate axis, identification line and identification mark;

[0066] Use OCR technology to automatically identify and judge questions and answers;

[0067] Determine the knowledge points included in the above questions, obtain the total score of each knowledge point based on the above answers, and convert it into an electronic format.

[0068] The computer device of the present invention calls the artificial intelligence-based online learning diagnostic program stored in the memory 101 through the processor 102, and further performs the following operations:

[0069] Calculate the total score of a test paper or homework;

[0070] The excellent rate, pass rate and average score are obtained based on the total scores of all students in the assessment, and the above-mentioned assessment entity is a class or grade.

[0071] The computer device of the present invention calls the artificial intelligence-based online learning diagnostic program stored in the memory 101 through the processor 102, and further performs the following operations:

[0072] According to the test papers or homeworks to be analyzed, the answer contents of the test papers or homeworks to be analyzed, and the corresponding total scores of each knowledge point, the first training set is updated to further train the first neural network model.

[0073] The computer device of the present invention calls the artificial intelligence-based online learning diagnostic program stored in the memory 101 through the processor 102, and further performs the following operations:

[0074] According to the total scores of each knowledge point corresponding to the above-mentioned test paper or homework to be analyzed, and the teaching suggestions for the test paper or homework to be analyzed, the above-mentioned second training set is updated, and the second neural network model is further trained.

[0075] This embodiment uses the above scheme to collect data of student test papers and homeworks through OCR technology as the first training set, and trains to obtain the first neural network model; the test paper or homework, the corresponding total score of each knowledge point, and the teaching suggestions are used as the second training set to train to obtain the second neural network model; the answer content of the test paper or homework to be analyzed is obtained through the handwriting of the electronic pen, and the test paper or homework to be analyzed is input into the first neural network model to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed. Among them, the knowledge points of the test paper or homework are fixed, that is, the knowledge points corresponding to each question can be obtained according to the test paper or homework to be analyzed; the total score of each knowledge point corresponding to the test paper or homework to be analyzed is input into the second neural network model to obtain the teaching suggestions for the test paper or homework to be analyzed; it can quickly and accurately evaluate the students' true mastery of each knowledge point, and give appropriate teaching suggestions, which not only saves teachers' time and energy, but also helps students quickly find out the gaps and improve their grades.

[0076] Based on the above hardware structure, an embodiment of the online learning diagnosis method based on artificial intelligence of the present invention is proposed.

[0077] Reference Figure 2 , Figure 2 This is a flow chart of the first embodiment of the online learning diagnosis method based on artificial intelligence of the present invention.

[0078] like Figure 2 As shown, in the first embodiment, the online learning diagnosis method based on artificial intelligence of the embodiment of the present invention includes the following steps:

[0079] Step S10. Collect the data of student test papers and homework as the first training set through OCR technology, and train to obtain the first neural network model; the data of the above-mentioned student history test papers and homework include multiple questions, the knowledge points corresponding to each question, and the answer content of each question; the data of the student history test papers and homework also include the total score of each knowledge point of each test paper or homework.

[0080] Among them, when a knowledge point only appears in one question, the total score of the knowledge point is the score of the knowledge point in the question; when a knowledge point appears in multiple questions, the total score of the knowledge point is the sum of the scores of the knowledge point in each question where the knowledge point appears.

[0081] Step S20. Use the test paper or homework, the corresponding total score of each knowledge point, and the teaching suggestions as the second training set to train a second neural network model.

[0082] Step S30. The answer content of the test paper or homework to be analyzed is obtained through the handwriting of the electronic pen, and the answer content is input into the first neural network model in combination with the test paper or homework to be analyzed to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed. Among them, the knowledge points of the test paper or homework are fixed, that is, the knowledge point corresponding to each question can be obtained according to the test paper or homework to be analyzed.

[0083] Step S40: Input the total scores of each knowledge point corresponding to the test paper or homework to be analyzed into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed.

[0084] In this embodiment, the first neural network model and the second neural network model are both deep neural network models.

[0085] The online learning diagnosis method of the embodiment of the present invention obtains the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, and inputs the answer content of the test paper or homework to be analyzed into the first neural network model in combination to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed, and then inputs the test paper or homework to be analyzed and the corresponding total score of each knowledge point into the second neural network model to obtain the teaching suggestions for the test paper or homework to be analyzed. Therefore, the present invention can quickly and accurately evaluate the students' true mastery of each knowledge point and give appropriate teaching suggestions, which not only saves teachers' time and energy, but also helps students quickly find omissions and improve their grades.

[0086] Further, Figure 3 FIG. 2 is a flow chart of the second embodiment of the online learning diagnosis method based on artificial intelligence of the present invention. Figure 3 As shown, based on the first embodiment, a second embodiment of the online learning diagnosis method based on artificial intelligence of the present invention is proposed. In this embodiment, in the above step S10, the data of student test papers and homework are collected by OCR technology, which specifically includes the following steps:

[0087] Step S11: Divide the paper test paper or homework into multiple modular areas according to different topics, and set the main coordinate axis, identification line and identification mark. Each modular area has one topic.

[0088] Step S12: Collect the written content of each modular area, and identify the content area according to the above-mentioned main coordinate axis, identification line and identification mark.

[0089] Step S13: Use OCR technology to automatically identify and judge the questions and their answers.

[0090] Step S14. Determine the knowledge points included in the above questions according to the above questions, obtain the total score of each knowledge point according to the above answer content, and convert it into an electronic format.

[0091] Among them, OCR (Optical Character Recognition) refers to the process in which an electronic device (such as a scanner or digital camera) examines characters printed on paper, determines their shapes by detecting dark and light patterns, and then uses character recognition methods to translate the shapes into computer text for further editing and processing by word processing software.

[0092] In this embodiment, the above step S10 further includes:

[0093] Step S15. Use the collected data of student test papers and homework as the first training set to train and obtain the first neural network model.

[0094] Further, Figure 4 FIG. 2 is a flow chart of the third embodiment of the online learning diagnosis method based on artificial intelligence of the present invention. Figure 4 As shown, based on the first embodiment, a third embodiment of the online learning diagnosis method based on artificial intelligence of the present invention is proposed. In this embodiment, the answer content of the test paper or homework to be analyzed is obtained by the handwriting of the electronic pen in the above step S30, which specifically includes:

[0095] Step S31: Collect the stroke order information and position information of the electronic pen to form different strokes.

[0096] Step S32. Obtain the input characters according to the stroke combination to obtain the answer content; the above characters include text, numbers, English or symbols.

[0097] It is understandable that for different question types or questions, the corresponding characters constituting the answer content are different.

[0098] In this embodiment, the above step S30 further includes:

[0099] Step S33. Input the first neural network model in combination with the test paper or homework to be analyzed to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed.

[0100] Further, Figure 5 FIG. 4 is a flow chart of the fourth embodiment of the online learning diagnosis method based on artificial intelligence of the present invention. Figure 5 As shown, based on the third embodiment, a fourth embodiment of the online learning diagnosis method based on artificial intelligence of the present invention is proposed. In this embodiment, after the total score of each knowledge point corresponding to the test paper or homework to be analyzed is obtained in the above step S3, it also includes:

[0101] Step S34: Calculate the total score of a test paper or homework.

[0102] Step S35. Obtain the excellent rate, pass rate and average score based on the total scores of all students in the assessment, where the assessment is for a class or grade.

[0103] Optionally, the online learning diagnosis method of this embodiment further includes:

[0104] According to the test papers or homeworks to be analyzed, the answer contents of the test papers or homeworks to be analyzed, and the corresponding total scores of each knowledge point, the first training set is updated to further train the first neural network model.

[0105] It is understandable that subsequent questions to be analyzed can obtain more accurate total scores for each knowledge point through further training of the first neural network model, so that teachers can more accurately judge students' weak knowledge points and mastered knowledge points.

[0106] Optionally, the online learning diagnosis method of this embodiment further includes:

[0107] According to the above-mentioned test papers or homeworks to be analyzed and the corresponding total scores of each knowledge point, as well as the teaching suggestions for the test papers or homeworks to be analyzed, the above-mentioned second training set is updated to further train the second neural network model.

[0108] In this embodiment, subsequent questions to be analyzed can obtain more accurate teaching suggestions through the further trained second neural network model, so as to achieve maximum efficiency in answering questions and provide strong support for improving grades.

[0109] It should be noted that the above teaching suggestions include: when a certain knowledge point has a large number of deductions, that is, a small total score, it is recommended to copy the knowledge point multiple times and do corresponding exercises to strengthen memory; when a certain knowledge point has a small number of deductions, that is, a large total score, it is recommended to copy the knowledge point twice to strengthen memory. The above teaching suggestions may also include: when a question contains multiple knowledge points, it is assumed to be a more difficult question, and a separate exercise book can be formed based on multiple knowledge points, and even personalized questions can be provided for students to consolidate their practice.

[0110] Reference Figure 6 , Figure 6 This is a functional module diagram of the first embodiment of the online learning diagnosis device based on artificial intelligence of the present invention.

[0111] The first embodiment of the online learning diagnosis device based on artificial intelligence of the present invention includes a first acquisition module 10, a first neural network model 20, a second acquisition module 30 and a second neural network model 40.

[0112] The first acquisition module 10 is used to collect data on student test papers and homework as a first training set through OCR technology; the data on the student history test papers and homework include multiple questions, knowledge points corresponding to each question, and the answer content of each question; and also include the total score of each knowledge point of each test paper or homework.

[0113] The first neural network model 20 is trained by the first training set. The first neural network model 20 is used to input the test paper or homework to be analyzed, obtain the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, and output the total score of each knowledge point corresponding to the test paper or homework to be analyzed.

[0114] The second acquisition module 30 is used to acquire the test paper or homework, the corresponding total score of each knowledge point, and the teaching suggestions as the second training set.

[0115] The second neural network model 40 is trained by the second training set. The second neural network model 40 is used to input the test paper or homework to be analyzed and the corresponding total scores of each knowledge point, and output teaching suggestions for the test paper or homework to be analyzed.

[0116] Among them, the steps for implementing each functional module of the online learning diagnosis device based on artificial intelligence can refer to the various embodiments of the online learning diagnosis device based on artificial intelligence of the present invention, and will not be repeated here.

[0117] Further, Figure 7 FIG. 2 is a functional module diagram of the second embodiment of the online learning diagnosis device based on artificial intelligence of the present invention. Figure 7 As shown, based on the first embodiment of the online learning diagnosis device, a second embodiment of the online learning diagnosis device based on artificial intelligence of the present invention is proposed. In this embodiment, the above-mentioned online learning diagnosis device based on artificial intelligence also includes a storage module 50 and an integration module 60.

[0118] The storage module 50 is used to store the student ID, all test papers or homework completed by the student ID and the corresponding total scores of each knowledge point, and all teaching suggestions.

[0119] The above-mentioned integration module 60 is used to integrate all the test papers or homeworks completed by the student ID within the time period and the corresponding total scores of each knowledge point, as well as all teaching suggestions at regular intervals, to obtain the knowledge points and the corresponding total scores, and generate a personal knowledge graph of the student ID.

[0120] It should be noted that the integration module 60 can also sort the total scores of each knowledge point. Optionally, the integration module 60 is also used to preset an interval time period to facilitate interval integration.

[0121] In other embodiments, the integration module 60 is further configured to preset a score threshold.

[0122] In this embodiment, after ranking the total scores of each knowledge point, a ranking report can also be generated. The lower the total score of a knowledge point in the ranking report, the less the student's mastery of the knowledge point is. The knowledge points with total scores below the score threshold in the ranking report are the knowledge points that the student needs to strengthen.

[0123] Therefore, according to the above ranking report, we can also prioritize and strengthen the study of knowledge points whose total scores are lower than the score threshold. On the one hand, it can help students to study more targetedly to make up for their weaknesses. On the other hand, based on time considerations, we can improve students' learning effects as quickly as possible within a limited time.

[0124] Optionally, the first acquisition module 10 is specifically used to collect the stroke order information and position information of the electronic pen to form different strokes; and obtain input characters according to the stroke combination to obtain the answer content; the above characters include text, numbers, English or symbols.

[0125] Furthermore, the above-mentioned artificial intelligence-based online learning diagnosis device also includes a comparison module.

[0126] The comparison module is used to calculate the total score of a test paper or homework. The comparison module is also used to obtain the excellent rate, pass rate and average score based on the total score of all students to reflect the results and overall distribution of each training assessment. The above assessment is a class or grade; that is, for a class exam, the excellent rate, pass rate and average score of the class can be known through the comparison module; for a grade exam, the excellent rate, pass rate and average score of the grade can be known through the comparison module.

[0127] The comparison module is also used to obtain the performance track based on the total score of each test paper or homework, and calculate the student's ranking, progress or regression, so as to generate a personal performance report. Through the student's personal performance report, the teacher can quickly learn the student's performance track, ranking, and progress or regression, and then judge the student's recent learning status, so as to better communicate with the student and better help the student's learning.

[0128] In addition, this embodiment further provides a storage medium, on which an online learning diagnosis program based on artificial intelligence is stored. When the online learning diagnosis program based on artificial intelligence is executed by a processor, the following operations are implemented:

[0129] The data of student test papers and homeworks are collected through OCR technology as the first training set, and the first neural network model is trained; the data of the above-mentioned student history test papers and homeworks include multiple questions, the knowledge points corresponding to each question, and the answer content of each question; the data of student history test papers and homeworks also include the total score of each knowledge point of each test paper or homework.

[0130] The test papers or homework, the corresponding total scores of each knowledge point, and the teaching suggestions are used as the second training set to train a second neural network model.

[0131] The answer content of the test paper or homework to be analyzed is obtained through the handwriting of the electronic pen, and the test paper or homework to be analyzed is input into the first neural network model to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed. Among them, the knowledge points of the test paper or homework are fixed, that is, the knowledge point corresponding to each question can be obtained according to the test paper or homework to be analyzed.

[0132] The total scores of each knowledge point corresponding to the test paper or homework to be analyzed are input into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed.

[0133] Furthermore, when the above-mentioned artificial intelligence-based online learning diagnosis program is executed by the processor, the following operations are also implemented:

[0134] Collect the stroke order information and position information of the electronic pen to form different strokes;

[0135] The input characters are obtained according to the stroke combination to obtain the answer content; the above characters include words, numbers, English or symbols.

[0136] Furthermore, when the above-mentioned artificial intelligence-based online learning diagnosis program is executed by the processor, the following operations are also implemented:

[0137] Divide the paper test paper or homework into multiple modular areas according to different topics, and set the main coordinate axis, identification line and identification mark; each modular area has one topic;

[0138] Collect the written content of each modular area, and identify the content area according to the above-mentioned main coordinate axis, identification line and identification mark;

[0139] Use OCR technology to automatically identify and judge questions and answers;

[0140] Determine the knowledge points included in the above questions, obtain the total score of each knowledge point based on the above answers, and convert it into an electronic format.

[0141] Furthermore, when the above-mentioned artificial intelligence-based online learning diagnosis program is executed by the processor, the following operations are also implemented:

[0142] Calculate the total score of a test paper or homework;

[0143] The excellent rate, pass rate and average score are obtained based on the total scores of all students in the assessment, and the above-mentioned assessment entity is a class or grade.

[0144] Furthermore, when the above-mentioned artificial intelligence-based online learning diagnosis program is executed by the processor, the following operations are also implemented:

[0145] According to the test papers or homeworks to be analyzed, the answer contents of the test papers or homeworks to be analyzed, and the corresponding total scores of each knowledge point, the first training set is updated to further train the first neural network model.

[0146] Furthermore, when the above-mentioned artificial intelligence-based online learning diagnosis program is executed by the processor, the following operations are also implemented:

[0147] According to the total scores of each knowledge point corresponding to the above-mentioned test paper or homework to be analyzed, and the teaching suggestions for the test paper or homework to be analyzed, the above-mentioned second training set is updated, and the second neural network model is further trained.

[0148] Through the above scheme, this embodiment uses OCR technology to collect data on student test papers and homework as the first training set, and trains to obtain a first neural network model; uses the test paper or homework, the corresponding total scores of each knowledge point, and teaching suggestions as the second training set, and trains to obtain a second neural network model; obtains the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, and inputs it into the first neural network model in combination with the test paper or homework to be analyzed to obtain the total scores of each knowledge point corresponding to the test paper or homework to be analyzed; inputs the total scores of each knowledge point corresponding to the test paper or homework to be analyzed into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed; it can not only quickly and accurately evaluate the students' true mastery of each knowledge point, avoid the identification errors of weak knowledge points due to data structural deviations, and help teachers fully grasp the students' learning situation, but also give appropriate teaching suggestions to help students quickly master knowledge points and improve learning efficiency.

[0149] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0150] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0151] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An online learning diagnosis method based on artificial intelligence, characterized in that: The online learning diagnosis method based on artificial intelligence includes: The data of student test papers and homework are collected as a first training set by using OCR technology, and a first neural network model is obtained by training; the data of the student history test papers and homework include a plurality of questions, a knowledge point corresponding to each question, and the answer content of each question; and also include the total score of each knowledge point of each test paper or homework; The test papers or homework, the corresponding total scores of each knowledge point, and the teaching suggestions are used as the second training set to train a second neural network model; The answer content of the test paper or homework to be analyzed is obtained through the handwriting of the electronic pen, and the answer content is input into the first neural network model in combination with the test paper or homework to be analyzed to obtain the total score of each knowledge point corresponding to the test paper or homework to be analyzed; Inputting the total scores of each knowledge point corresponding to the test paper or homework to be analyzed into the second neural network model to obtain teaching suggestions for the test paper or homework to be analyzed; The data of student test papers and homework collected by OCR technology specifically includes: Divide the paper test paper or homework into multiple modular areas according to different topics, and set the main coordinate axis, identification line and identification mark; each modular area has one topic; Collecting the written content of each modular area, and identifying the content area according to the main coordinate axis, identification line and identification mark; Use OCR technology to automatically identify and judge questions and answers; Determine the knowledge points included in the question according to the question, obtain the total score of each knowledge point according to the answer content, and convert it into an electronic format; The method further comprises: According to the test paper or homework to be analyzed, the answer content of the test paper or homework to be analyzed, and the total score of each corresponding knowledge point, the first training set is updated to further train the first neural network model; When a knowledge point appears in only one question, the total score of the knowledge point is the score of the knowledge point in the question; when a knowledge point appears in multiple questions, the total score of the knowledge point is the sum of the scores of the knowledge point in each question where the knowledge point appears; The method further comprises: According to the total scores of each knowledge point corresponding to the test paper or homework to be analyzed and the teaching suggestions of the test paper or homework to be analyzed, the second training set is updated to further train the second neural network model; The method further comprises: Store the student ID, all test papers or homework completed by the student ID and the corresponding total scores of each knowledge point, as well as all teaching suggestions; At regular intervals, all test papers or homework completed by the student ID within the time period, the corresponding total scores of each knowledge point, and all teaching suggestions are integrated to obtain the knowledge points and the corresponding total scores, and generate a personal knowledge graph for the student ID; Sort the total scores of each knowledge point and generate a ranking report; A score threshold is preset, and the knowledge points in the sorting report whose total scores are lower than the score threshold are regarded as the knowledge points that the student needs to strengthen his / her learning.

2. The online learning diagnosis method based on artificial intelligence according to claim 1, characterized in that: The method of obtaining the answer content of the test paper or homework to be analyzed by the handwriting of the electronic pen specifically includes: Collect the stroke order information and position information of the electronic pen to form different strokes; The input characters are obtained according to the stroke combination to obtain the answer content; the characters include words, numbers, English or symbols.

3. The online learning diagnosis method based on artificial intelligence according to claim 1, characterized in that: After obtaining the total score of each knowledge point corresponding to the test paper or homework to be analyzed, the method further includes: Calculate the total score of a test or assignment; The excellent rate, passing rate and average score are obtained based on the total scores of all students in the assessment, and the assessment entity is a class or grade.

4. An artificial intelligence-based online learning diagnosis device for implementing the method of claim 1, characterized in that: The online learning diagnosis device based on artificial intelligence comprises: A first acquisition module is used to collect data of student test papers and homework as a first training set through OCR technology; the data of the student history test papers and homework each includes a plurality of questions, a knowledge point corresponding to each question, and the answer content of each question; and also includes the total score of each knowledge point of each test paper or homework; The first neural network model is trained by the first training set, and is used to input the test paper or homework to be analyzed, and obtain the answer content of the test paper or homework to be analyzed through the handwriting of the electronic pen, and output the total score of each knowledge point corresponding to the test paper or homework to be analyzed; A second acquisition module is used to acquire the test paper or homework, the corresponding total score of each knowledge point, and the teaching suggestions as the second training set; The second neural network model is trained by the second training set, and is used to input the total scores of each knowledge point corresponding to the test paper or homework to be analyzed, and output teaching suggestions for the test paper or homework to be analyzed; The online learning diagnosis device also includes: A storage module is used to store the student ID, all test papers or homework completed by the student ID and the corresponding total scores of each knowledge point, and all teaching suggestions; The integration module is used to integrate all the test papers or homeworks completed by the student ID within the time period and the corresponding total scores of each knowledge point, as well as all teaching suggestions at regular intervals, to obtain the knowledge points and the corresponding total scores, and to sort the total scores of each knowledge point.

5. The online learning diagnosis device based on artificial intelligence as claimed in claim 4, characterized in that: The first acquisition module is specifically used to collect the stroke order information and position information of the electronic pen to form different strokes; and to obtain input characters according to the stroke combination to obtain the answer content; the characters include text, numbers, English or symbols.

6. The online learning diagnosis device based on artificial intelligence according to claim 4, characterized in that: The online learning diagnosis device also includes: A comparison module is used to calculate the total score of a test paper or homework, and obtain the excellent rate, pass rate and average score based on the total score of all students in the assessment, where the assessment is for a class or grade; The comparison module is also used to obtain the score track based on the total score of each test paper or homework, and calculate the student's ranking, progress or regression.

Images