Student examination and evaluation method and system based on AI big data model

Abstract

The invention relates to the technical field of examination and evaluation, in particular to a student examination and evaluation method and system based on an AI big data model. Comprising the following steps: S1, collecting historical examination and evaluation data, establishing an AI big data model, and then dividing the AI big data model into a learning distribution module, a training distribution module, an examination module and a comprehensive scoring module; s2, a learning distribution module analyzes the predicted learning duration of each student, performs learning course generation according to the predicted learning duration in combination with the student basic data, and divides the learning courses into online courses and offline courses; the AI big data model is used for analysis and prediction, students can be evaluated more accurately, a more reasonable learning plan can be made for the students by predicting the learning duration, meanwhile, a teacher can better arrange teaching resources, and the teaching efficiency is improved. The learning efficiency score and the examination score can accurately reflect the knowledge mastering degree and the application ability of the student.

Description

Technical Field

[0001] The present invention relates to the field of assessment technology, and in particular to a student assessment method and system based on an AI big data model. Background Art

[0002] Existing technologies usually evaluate students through traditional methods such as test scores and classroom performance. The purpose is to measure the students' mastery of knowledge and determine their learning outcomes, so as to provide a basis for teaching adjustments, thereby improving teaching quality and students' learning outcomes; However, traditional evaluation methods are often too single and rely mainly on test scores, which makes it difficult to fully reflect the students' learning process and comprehensive abilities. This may lead to inaccurate evaluation of students and an inability to truly understand their strengths and weaknesses, thus affecting the pertinence and effectiveness of teaching. At the same time, there is a lack of personalized evaluation, and customized evaluation cannot be performed according to the characteristics and needs of each student, making it difficult to meet the learning needs of different students. The evaluation method is usually static and cannot track students' learning progress in real time, making it difficult to adjust teaching strategies in a timely manner. Therefore, a student assessment method and system based on an AI big data model is proposed. Summary of the invention

[0003] The purpose of the present invention is to provide a student assessment method and system based on AI big data model to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, one of the purposes of the present invention is to provide a student assessment method based on an AI big data model, comprising the following steps: S1. Collect historical assessment data, build an AI big data model, and then divide the AI ​​big data model into a learning allocation module, a training allocation module, an examination assessment module, and a comprehensive scoring module; S2. The learning allocation module analyzes the predicted learning time of each student, generates learning courses based on the predicted learning time and the basic information of the student, and divides the learning courses into online courses and offline courses; S3, the training allocation module generates training content based on online courses and offline courses, and divides the training content into multiple sections, sets qualification standards for each section of training content, obtains the training data of the trainees, and updates the training content based on the qualification standards; S4, the examination and assessment module connects to the instructor side to set the examination, obtains the training content that the trainees have reached the qualified standard from the training allocation module, and generates examination questions based on the training content that has reached the qualified standard; S5. The comprehensive scoring module conducts a comprehensive analysis of the students' scores based on the learning allocation module, training allocation module, examination and assessment module, and the instructor side to form the students' total score.

[0005] As a further improvement of the technical solution, the step of S1 is as follows: S1.1. By establishing data transmission connections with the student side and the instructor side, collect data related to learning, training, and examinations, summarize them into historical assessment data, and then establish an AI big data model based on the historical assessment data; S1.2. Divide the AI ​​big data model into four modules, namely learning allocation module, training allocation module, examination and assessment module, and comprehensive scoring module.

[0006] As a further improvement of the technical solution, the steps of S2 are as follows: S2.1. Obtain each student's historical life data on the student side, obtain each student's test date on the instructor side, and then analyze the learning period based on the real-time time combined with the test date, and then perform a predicted learning time analysis based on the historical life data combined with the learning period, so as to obtain the predicted learning time of each student; S2.2. Obtain the basic information of each student on the student side, and at the same time obtain the assignable learning courses, and then generate the learning course allocation based on the predicted learning time combination of the student basic information and the assignable learning courses, so as to obtain the corresponding online and offline courses for each student.

[0007] As a further improvement of the technical solution, the steps of S3 are as follows: S3.1. Generate training content based on the online and offline courses corresponding to the trainees, and divide them into multiple sections according to the differences in the training content. At the same time, analyze the qualification standards for each section of the training content, so as to set the qualification standards for each section of the training content; S3.2. Obtain the trainee's training data, and then compare the training data with the qualification standards of the corresponding training content. When the training data meets the qualification standards, update the trainee's training content and open the next section of training content. Conversely, when the training data does not meet the qualification standards, keep the training content unchanged.

[0008] As a further improvement of the technical solution, the step of S4 is as follows: S4.1. Collect test scoring standards and test difficulty settings from teachers on the teacher side; S4.2. On the assessment day, the training content that the trainee has reached the qualified standard is obtained from the training allocation module, and then the test questions are generated according to the training content that has reached the qualified standard and the test difficulty, and the test questions are sent to the trainee through the trainee terminal; S4.3. Collect the students' completed content of the test questions, automatically grade the test questions in combination with the completed content, and obtain the students' test scores in this test.

[0009] As a further improvement of the present technical solution, the formula of S4 is as follows: ; Among them, P hard is the proportion of high-difficulty questions, P medium The proportion of medium-difficulty questions, P easy For the ratio of low-difficulty questions, adjust these ratios according to the exam difficulty setting.

[0010] As a further improvement of the technical solution, the step of S5 is as follows: S5.1. Combine the students’ actual learning time with the predicted learning time to score their learning time; S5.2. Combine the training content that has reached the qualified standard with the total training content to evaluate the learning efficiency; S5.3. Test and grade the students’ test scores and test standards; S5.4. Collect personal ratings of students from teachers; S5.5. Assign evaluation weights based on the teacher's assessment of the learning time score, learning efficiency score, test score and personal score. Then, the learning time score, learning efficiency score, test score and personal score are combined to form the student's total score, and the total score is fed back to the teacher.

[0011] As a further improvement of the present technical solution, the formula of S5 is as follows: ; Among them, R s is the learning time deviation rate, L s is the actual learning time of the students, L y To predict the duration of study; ; Among them, E s is learning efficiency, N s is the number of training contents that have reached the qualified standard, N y is the total number of training contents; ; Among them, R k is the test score rate, S i S is the test score for the students. j is the total score of the examination standard; ; Among them, S k is the total score, α1 is the learning time score weight, α2 is the learning efficiency score weight, α3 is the test score weight, α4 is the personal score weight, Js The personal rating value.

[0012] The second object of the present invention is to provide a student assessment and evaluation system based on an AI big data model, including any one of the above-mentioned student assessment and evaluation methods based on an AI big data model, including a model building unit, an exam generation unit and a comprehensive scoring unit; The model building unit is used to build an AI big data model, and then divide the AI ​​big data model into a learning allocation module, a training allocation module, an examination and assessment module, and a comprehensive scoring module; The test generation unit is used to divide the learning courses into online courses and offline courses, obtain the training data of the students and update the training content in combination with the qualification standards, and generate test questions based on the training content that has reached the qualification standards; The comprehensive scoring unit is used to conduct a comprehensive analysis of the scores of the students based on the learning allocation module, the training allocation module, the examination and assessment module and the instructor side to form an overall score for the students.

[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. A student assessment method and system based on AI big data model, which can more accurately assess students by using AI big data model for analysis and prediction. By predicting the learning time, a more reasonable learning plan can be formulated for students. It also helps teachers to better arrange teaching resources. The learning efficiency score and test score can accurately reflect the students' mastery of knowledge and application ability.

[0014] 2. A student assessment method and system based on an AI big data model. Through multi-source data collection, including historical life data, learning and training test data from the student side, and assessment date, personal score and other information from the instructor side, the system can fully understand the student's learning status and ability level. It is no longer limited to traditional test scores, but comprehensively considers various factors in the learning process, such as learning time, learning efficiency, training performance, etc., to achieve a comprehensive assessment of the students.

[0015] 3. A student assessment method and system based on an AI big data model generates personalized online and offline courses and corresponding training content for each student based on the student's basic information, learning preferences, predicted learning time and other factors. This personalized learning plan can meet the needs of different students and improve learning outcomes. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is the overall flow chart of the present invention; Figure 2 A flowchart of establishing an AI big data model for the present invention; Figure 3 A flowchart of the process of obtaining online courses and offline courses corresponding to each student for the present invention; Figure 4 A flowchart of the present invention for updating the training content of trainees; Figure 5 A flowchart of the present invention for obtaining the test scores of students in this test; Figure 6 A flowchart of forming the total score of the student for the present invention; Figure 7 The structural principle diagram of the unit for model building of the present invention.

[0017] The meaning of each number in the figure is: 10. Model building unit; 20. Test generation unit; 30. Comprehensive scoring unit. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] like Figure 1 - Figure 7 As shown, one of the purposes of the present invention is to provide a student assessment method based on an AI big data model, comprising the following steps: S1. Collect historical assessment data, build an AI big data model, and then divide the AI ​​big data model into a learning allocation module, a training allocation module, an examination assessment module, and a comprehensive scoring module; The steps of S1 are as follows: S1.1. By establishing data transmission connections with the student side and the instructor side, collect data related to learning, training, and examinations, summarize them into historical assessment data, and then establish an AI big data model based on the historical assessment data; S1.2. Divide the AI ​​big data model into four modules, namely, learning allocation module, training allocation module, examination and assessment module, and comprehensive scoring module. The specific steps are as follows: Student-side data collection: collect learning data, training data, and test data; Teacher-side data collection: collect teaching evaluation data and homework correction data; Aggregate these data into historical assessment data; AI big data model module design: The learning allocation module is used to allocate personalized learning tasks and resources to students. The training allocation module is used to allocate appropriate training tasks to students based on learning tasks. The examination and assessment module is used to design personalized examination plans, including examination content, difficulty level, etc. The comprehensive scoring module is used to integrate data from various aspects such as learning, training, and examinations to give students a comprehensive score.

[0020] S2. The learning allocation module analyzes the predicted learning time of each student, generates learning courses based on the predicted learning time and the basic information of the student, and divides the learning courses into online courses and offline courses; The steps of S2 are as follows: S2.1. Obtain each student's historical life data on the student side, obtain each student's test date on the teacher side, and then analyze the learning period based on the real-time time combined with the test date. Then, perform a predicted learning time analysis based on the historical life data combined with the learning period, so as to obtain the predicted learning time of each student. The specific steps are as follows: Obtain each student's historical life data on the student side. This data may include but is not limited to: the distribution of daily study time in the past period of time, the frequency of participating in learning activities, and life habit data, such as average sleep time, entertainment activity time, etc., which may affect the learning status and duration; At the same time, the teacher obtains the assessment date of each student; Study period analysis: Determine the time period between the real time and the assessment date as the study period, and analyze the learning patterns of students in similar time periods in historical life data, such as whether they will increase their study time when the assessment is approaching, whether their learning efficiency changes, etc. Predicted learning time analysis: Combined with the learning time patterns in historical life data and the results of the learning period analysis, taking into account the possible impact of students' personal characteristics and recent life changes on learning time, the formula is as follows: ; Among them, T s is the remaining days of the study period, T k T is the assessment day. z is the real time; ; Among them, L i is the historical average daily study time, L z is the total time of history learning, D i Study days for history; ; Among them, C iis the learning urgency coefficient, α is a parameter adjusted according to historical data (reflecting the impact of urgency on learning time), T g is the total number of days during the study period; ; Among them, L y To predict the learning time, L g Adjust duration for personal factors.

[0021] S2.2. Obtain the basic information of each student on the student side, and obtain the allocable learning courses at the same time. Then, according to the predicted learning time, the basic information of the students and the allocable learning courses are combined to generate the learning course allocation, so as to obtain the online and offline courses corresponding to each student. The specific steps are as follows: Obtain basic information and allocable learning courses: Obtain basic information of each student on the student side, including learning ability assessment, learning preferences, time constraints, and obtain allocable learning course information, including course type, course difficulty level, course duration, course content overview, and applicable population; Learning course allocation generation: First, a preliminary match is made based on the student's learning ability assessment results and the course difficulty level. Then, the course allocation is adjusted based on the student's learning preferences. Next, the student's schedule constraints and predicted learning time are considered. Finally, the type of course and the overall situation of the student are comprehensively considered to determine the corresponding online and offline course combination for each student.

[0022] S3, the training allocation module generates training content based on online courses and offline courses, and divides the training content into multiple sections, sets qualification standards for each section of training content, obtains the training data of the trainees, and updates the training content based on the qualification standards; The steps of S3 are as follows: S3.1. Generate training content based on the online and offline courses corresponding to the trainees, and divide them into multiple sections according to the differences in the training content. At the same time, analyze the qualification standards for each section of the training content, so as to set the qualification standards for each section of the training content. The specific steps are as follows: Generate training content: For online courses, analyze the knowledge structure, teaching objectives and teaching methods of the course, and determine the corresponding online exercises, homework, discussion topics and other training content based on the course content, such as basic knowledge training, knowledge competition, training topic library and training archives; For offline courses, consider the practical nature and interactive needs of the courses. Generate training content such as experimental projects, group discussion tasks, field investigation activities, such as virtual simulation, scenario-based sandbox collaborative confrontation training, virtual simulation scenario-based training for training and preparation, resource status, and on-site situation mastery; Divide the training content into segments: According to the logical structure of the course and the learning progress, divide the training content into multiple stages or segments. It can be divided according to the difficulty of the knowledge points and the order of learning; Analysis and setting of qualification standards: For each training content, analyze its goals and requirements, determine the key indicators to measure whether the trainees have reached the qualification standards, and then for knowledge-based training content, consider indicators such as test scores and homework completion quality. For practical training content, it can be evaluated based on task completion, skill mastery, etc., refer to historical data and industry standards, make reasonable adjustments to the qualification standards, or set the qualification standards through instructors.

[0023] S3.2, obtain the trainee's training data, and then compare the training data with the qualification standards of the corresponding training content. When the training data meets the qualification standards, update the trainee's training content and open the next training content. On the contrary, when the training data does not meet the qualification standards, keep the training content unchanged. The specific steps are as follows: Obtain student training data: Collect student performance data on various training contents from the student side, the instructor side, and related learning management systems. For online courses, data such as student online test scores, homework submission, and study time can be obtained. For offline courses, data such as student classroom performance, completion of practical projects, and participation in group discussions can be collected. Qualification comparison: compare the obtained trainee training data with the qualification standards of the corresponding training content one by one; Processing based on the comparison results: When the training data meets the qualification criteria, the training content for the trainees is updated, the next stage of training content is opened, and a notification is sent to the trainees to inform them that they have successfully passed the current stage of training and can start the next stage of learning; When the training data does not meet the qualification standards, the training content remains unchanged, prompting students to continue working hard while providing targeted learning suggestions and resources.

[0024] S4, the examination and assessment module connects to the instructor side to set the examination, obtains the training content that the trainees have reached the qualified standard from the training allocation module, and generates examination questions based on the training content that has reached the qualified standard; The steps of S4 are as follows: S4.1. Collect test scoring standards and test difficulty settings from teachers on the teacher side; On the instructor side, the instructor determines the exam scoring criteria based on course requirements and teaching objectives; The instructor sets the difficulty of the exam, such as the breadth and depth of knowledge coverage, the complexity of the question types, such as whether it includes difficult comprehensive application questions, the time required for answering questions, etc. The formula is as follows: ; Among them, C type V represents the complexity coefficient of the question type, a quantitative indicator that comprehensively measures the overall complexity of all question types in this exam. The larger the value, the higher the overall complexity of the exam questions, and vice versa. type is the basic value of complexity of different question types, N type is the number of corresponding question types in the exam; ; Among them, T pressure is the time pressure coefficient, Q tatal is the total number of test questions, T duration is the test duration, S average The average speed at which students answer questions.

[0025] S4.2. On the assessment day, the training content that the trainee has reached the qualified standard is obtained from the training allocation module, and then the test questions are generated according to the training content that has reached the qualified standard and the test difficulty, and the test questions are sent to the trainee through the trainee terminal. The specific steps are as follows: Obtain qualified training content: On the assessment day, obtain the training content that the trainee has reached the qualified standard from the training allocation module, which is achieved by querying the trainee's learning record and training result database; Generate test questions: Determine the scope of test knowledge points based on the training content that has reached the qualification standard, ensure that the test content is closely related to the students' learning and training content, and then adjust the question type and difficulty level in combination with the test difficulty setting, and use random algorithms or templates to generate test questions to ensure the diversity and fairness of the test questions; Send test questions: Send the generated test questions to students through the student terminal. You can use online test platforms, emails, etc. to ensure that students can receive the test questions in time and clearly understand the time limit, answer requirements and other information of the test. The formula is as follows: ; Among them, P hard is the proportion of high-difficulty questions, P medium The proportion of medium-difficulty questions, P easy For the ratio of low-difficulty questions, adjust these ratios according to the exam difficulty setting.

[0026] S4.3. Collect the students' completed content of the test questions, automatically grade the test questions in combination with the completed content, and obtain the students' test scores in this test.

[0027] After students complete the test questions, the test system or related platforms collect the students' completed content of the test questions, summarize the students' scores on each question, and obtain the students' total score in this test.

[0028] S5. The comprehensive scoring module conducts a comprehensive analysis of the students' scores based on the learning allocation module, training allocation module, examination and assessment module, and the instructor side to form the students' total score.

[0029] The steps of S5 are as follows: S5.1. Combine the students’ actual learning time with the predicted learning time to score their learning time; ; Among them, R s is the learning time deviation rate, L s is the actual learning time of the students, L y In order to predict the learning time, the range of learning time score is set to 0-100 points, and the score is determined according to the learning time deviation rate. Linear mapping or piecewise function can be used. If the deviation rate is within a certain range, a higher score is given, and if the deviation is too large, the score is reduced.

[0030] S5.2. Combine the training content that has reached the qualified standard with the total training content to evaluate the learning efficiency; ; Among them, E s is learning efficiency, N s is the number of training contents that have reached the qualified standard, N y The total number of training contents is also scored in the range of 0-100, and the score is determined based on the learning efficiency.

[0031] S5.3. Test and grade the students’ test scores and test standards; ; Among them, R k is the test score rate, S i S is the test score for the students. j For the total score of the test standard, the score range is set to 0-100 points, and the score is determined based on the test score rate.

[0032] S5.4. Collect personal ratings of students from teachers; The instructor will make personal ratings based on the students' performance and directly obtain personal rating values ​​ranging from 0 to 100 points.

[0033] S5.5. Assign evaluation weights based on the teacher's assessment of the learning time score, learning efficiency score, test score, and personal score. Then, the learning time score, learning efficiency score, test score, and personal score are combined to form the student's total score, and the total score is fed back to the teacher. The formula is as follows: ; Among them, S k is the total score, α1 is the learning time score weight, α2 is the learning efficiency score weight, α3 is the test score weight, α4 is the personal score weight, J s is the personal rating value, and α1, α2, α3 and α4 are obtained by collecting evaluation weights from teachers.

[0034] The second object of the present invention is to provide a student assessment and evaluation system based on an AI big data model, including any one of the above-mentioned student assessment and evaluation methods based on an AI big data model, including a model building unit 10, an exam generation unit 20 and a comprehensive scoring unit 30; The model building unit 10 is used to build an AI big data model, and then divide the AI ​​big data model into a learning allocation module, a training allocation module, an examination and assessment module, and a comprehensive scoring module; The test generation unit 20 is used to divide the learning courses into online courses and offline courses, obtain the training data of the students and update the training content in combination with the qualification standards, and generate test questions based on the training content that has reached the qualification standards; The comprehensive scoring unit 30 is used to conduct a comprehensive analysis of the scores of the students based on the learning allocation module, the training allocation module, the examination and assessment module and the teacher's end to form a total score for the students.

[0035] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A student assessment method based on AI big data model, characterized by: The steps include: S1. Collect historical assessment data, build an AI big data model, and then divide the AI ​​big data model into a learning allocation module, a training allocation module, an examination assessment module, and a comprehensive scoring module; S2. The learning allocation module analyzes the predicted learning time of each student, generates learning courses based on the predicted learning time and the basic information of the student, and divides the learning courses into online courses and offline courses; S3, the training allocation module generates training content based on online courses and offline courses, and divides the training content into multiple sections, sets qualification standards for each section of training content, obtains the training data of the trainees, and updates the training content based on the qualification standards; S4, the examination and assessment module connects to the instructor side to set the examination, obtains the training content that the trainees have reached the qualified standard from the training allocation module, and generates examination questions based on the training content that has reached the qualified standard; S5. The comprehensive scoring module conducts a comprehensive analysis of the students' scores based on the learning allocation module, training allocation module, examination and assessment module, and the instructor side to form the students' total score.

2. The student assessment method based on the AI ​​big data model according to claim 1 is characterized by: The steps of S1 are as follows: S1.

1. By establishing data transmission connections with the student side and the instructor side, collect data related to learning, training, and examinations, summarize them into historical assessment data, and then establish an AI big data model based on the historical assessment data; S1.

2. Divide the AI ​​big data model into four modules, namely learning allocation module, training allocation module, examination and assessment module, and comprehensive scoring module.

3. The student assessment method based on AI big data model according to claim 1 is characterized by: The steps of S2 are as follows: S2.

1. Obtain each student's historical life data on the student side, obtain each student's test date on the instructor side, and then analyze the learning period based on the real-time time combined with the test date, and then perform a predicted learning time analysis based on the historical life data combined with the learning period, so as to obtain the predicted learning time of each student; S2.

2. Obtain the basic information of each student on the student side, and at the same time obtain the assignable learning courses, and then generate the learning course allocation based on the predicted learning time combination of the student basic information and the assignable learning courses, so as to obtain the corresponding online and offline courses for each student.

4. The student assessment method based on the AI ​​big data model according to claim 1 is characterized by: The steps of S3 are as follows: S3.

1. Generate training content based on the online and offline courses corresponding to the trainees, and divide them into multiple sections according to the differences in the training content. At the same time, analyze the qualification standards for each section of the training content, so as to set the qualification standards for each section of the training content; S3.

2. Obtain the trainee's training data, and then compare the training data with the qualification standards of the corresponding training content. When the training data meets the qualification standards, update the trainee's training content and open the next section of training content. Conversely, when the training data does not meet the qualification standards, keep the training content unchanged.

5. The student assessment method based on AI big data model according to claim 1 is characterized by: The steps of S4 are as follows: S4.

1. Collecting test scoring standards and test difficulty settings from teachers on the teacher side; S4.

2. On the assessment day, the training content that the trainee has reached the qualified standard is obtained from the training allocation module, and then the test questions are generated according to the training content that has reached the qualified standard and the test difficulty, and the test questions are sent to the trainee through the trainee terminal; S4.

3. Collect the students' completed content of the test questions, automatically grade the test questions in combination with the completed content, and obtain the students' test scores in this test.

6. The student assessment method based on AI big data model according to claim 1 is characterized by: The formula of S4 is as follows: ； Among them, P hard is the proportion of high-difficulty questions, P medium The proportion of medium-difficulty questions, P easy For the ratio of low-difficulty questions, adjust these ratios according to the exam difficulty setting.

7. The student assessment method based on AI big data model according to claim 1 is characterized by: The steps of S5 are as follows: S5.

1. Combine the students’ actual learning time with the predicted learning time to score their learning time; S5.

2. Combine the training content that has reached the qualified standard with the total training content to evaluate the learning efficiency; S5.

3. Test and grade the students’ test scores and test standards; S5.

4. Collect personal ratings of students from teachers; S5.

5. Assign evaluation weights based on the teacher's assessment of the learning time score, learning efficiency score, test score and personal score. Then, the learning time score, learning efficiency score, test score and personal score are combined to form the student's total score, and the total score is fed back to the teacher.

8. The student assessment method based on AI big data model according to claim 1 is characterized by: The formula of S5 is as follows: ； Among them, R s is the learning time deviation rate, L s is the actual learning time of the students, L y To predict the duration of study; ； Among them, E s is the learning efficiency, N s is the number of training contents that have reached the qualified standard, N y is the total number of training contents; ； Among them, R k is the test score rate, S i Score for students j is the total score of the examination standard; ； Among them, S k is the total score, α1 is the learning time score weight, α2 is the learning efficiency score weight, α3 is the test score weight, α4 is the personal score weight, J s The personal rating value.

9. A student assessment and evaluation system based on an AI big data model, used to implement a student assessment and evaluation method based on an AI big data model as described in any one of claims 1 to 7, characterized in that: It includes a model building unit (10), an exam generation unit (20), and a comprehensive scoring unit (30); The model building unit (10) is used to build an AI big data model, and then divide the AI ​​big data model into a learning allocation module, a training allocation module, an examination and assessment module, and a comprehensive scoring module; The test generation unit (20) is used to divide the learning courses into online courses and offline courses, obtain the training data of the students and update the training content in combination with the qualification standard, and generate test questions based on the training content that has reached the qualification standard; The comprehensive scoring unit (30) is used to conduct a comprehensive scoring analysis on the students based on the learning allocation module, the training allocation module, the examination and assessment module and the instructor side to form a total score for the students.

Images