Method and system for providing teacher-student matching and analysis results

Abstract

A method and system for providing teacher-student matching and analysis results are provided. A method for providing teacher-student matching and analysis results according to one embodiment of the present invention may include the steps of collecting teacher activity data and student activity data; labeling teacher characteristics and student characteristics; generating teacher vectors and student vectors; calculating similarity between vectors to generate a matching suitability score; providing matching results and matching reasons to a student terminal and providing student distribution and branding reports to a teacher terminal.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence-based educational platform technology, and more specifically, to a method and system that analyzes teacher activity data and student activity data to label teacher characteristics and student characteristics, calculates similarity between vectors generated based on this, provides optimal teacher-student matching, and provides a branding report to the teacher and a reason for matching to the student. Background Technology

[0002] It is emerging as a key factor in performance. In online tutoring, learning management services, and educational consulting platforms, recommending suitable teachers to students has a direct impact on service quality and learning effectiveness.

[0003] Traditional teacher-student matching methods primarily rely on basic filtering criteria such as subject, location, and price. It is common for students or parents to view a list of teachers meeting these criteria through search filters and make a selection by personally reviewing the teacher's educational background, experience, and student reviews. However, this approach has limitations as it fails to quantitatively evaluate a teacher's actual educational competence or suitability for the student, and it does not consider the compatibility between the student's learning style and the teacher's teaching style.

[0004] While some educational platforms have introduced teacher evaluation systems that provide student satisfaction scores or star ratings, these merely display overall average scores and fail to analyze teachers' specific strengths or teaching styles. Furthermore, because they do not consider students' individual characteristics or preferred feedback methods, they fail to reflect the fact that the same teacher may be effective for one student but not for another.

[0005] Meanwhile, collaborative filtering technology is widely utilized in the field of recommendation systems. Collaborative filtering provides recommendations by analyzing the selection patterns of similar users and has demonstrated high performance in e-commerce and content recommendation services. However, existing collaborative filtering technologies primarily focus on product or content recommendations and have limitations when directly applied to complex matching problems, such as teacher-student matching, which require consideration of educational outcomes and learning effectiveness.

[0006] Furthermore, existing systems focus solely on teacher recommendations from the student's perspective and provide almost no features that allow teachers to identify suitable students or brand their educational capabilities. There is a lack of systems that support teachers in identifying their strengths and utilizing them for promotion.

[0007] Therefore, there is a need for a system that quantifies teacher characteristics by comprehensively analyzing feedback quality, response speed, and the ability to improve student engagement, identifies students' learning tendencies and preferred feedback styles to provide optimal two-way matching, transparently explains the reasons for matching, and provides teachers with branding materials. The problem to be solved

[0008] The present invention has been devised to solve the aforementioned problems, and aims to provide a method and system for providing teacher-student matching and analysis results capable of providing optimal teacher-student matching by analyzing teacher activity data to label strength characteristics and feedback styles, analyzing student activity data to label learning tendencies and preferred feedback styles, and generating vectors based on this to calculate similarity. means of solving the problem

[0009] A method for providing teacher-student matching and analysis results according to an embodiment of the present invention for achieving the above objective may include: a method for providing teacher-student matching and analysis results by an information processing device, comprising the steps of: collecting teacher activity data including a teacher's subject, lecture information, feedback data, and response history data, and student activity data including a student's course enrollment history and lecture participation data; labeling teacher characteristics including a teacher's strength characteristics and feedback style based on the teacher activity data, and labeling student characteristics including a student's learning propensity and preferred feedback style based on the student activity data; generating a teacher vector based on the teacher characteristics and generating a student vector based on the student characteristics; calculating a similarity between the teacher vector and the student vector to calculate a teacher-student matching suitability score; and, based on the matching suitability score, providing at least one of the matched teacher information, the matching suitability score, and the matching reason to a student terminal, and providing at least one of the student distribution by preferred feedback style, a list of students with high matching suitability scores, and a teacher characteristic-based branding report to a teacher terminal.

[0010] Additionally, the step of labeling the teacher characteristics may include: determining the quality of feedback by analyzing at least one of the teacher's feedback text, feedback length, and student satisfaction based on the feedback data; determining the response speed by analyzing the time difference between the time of question registration and the time of answer provision based on the response history data; and determining the degree of improvement in participation by calculating the amount of change in student participation between the start and end times of the lecture course based on the lecture participation data.

[0011] Additionally, the step of calculating the matching suitability score may include: collecting characteristic data of teachers selected by other students with learning tendencies similar to the student; deriving a teacher characteristic pattern suitable for the student based on the characteristic data; and calculating the degree of agreement between the teacher characteristic pattern and the teacher characteristics of the teacher and reflecting it in the matching suitability score.

[0012] Additionally, the step of providing the matching reason may include: a step of analyzing the degree of alignment between the teacher's strength characteristics and the student's learning tendencies; a step of analyzing the degree of agreement between the teacher's feedback style and the student's preferred feedback style; and a step of converting the degree of alignment and the degree of agreement into text form and providing them as the matching reason.

[0013] A teacher-student matching and analysis result providing device according to another embodiment of the present invention for achieving the above objective includes a memory on which at least one program is recorded; and a processor that executes said program, and said program may include instructions for performing said method. Effects of the invention

[0014] According to the present invention as described above, by comprehensively analyzing the quality of teacher feedback, response speed, and degree of improvement in student participation to quantify teacher characteristics, and by identifying students' learning tendencies and preferred feedback styles, it is possible to maximize educational effectiveness by providing optimal matching in both directions.

[0015] In addition, by utilizing collaborative filtering techniques to analyze teacher selection patterns of students with similar learning tendencies and reflecting this in the matching process, it is possible to provide accurate recommendations based on actual learning data.

[0016] In addition, it enhances trust in teacher selection by transparently providing students with the reasons for matching, and supports teachers in identifying their strengths and utilizing them for marketing by providing reports on student distribution by preferred feedback style and branding. Brief explanation of the drawing

[0017] FIG. 1 is a diagram showing a system configuration according to one embodiment of the present invention. FIG. 2 is an overall flowchart of a method for providing teacher-student matching and analysis results according to one embodiment of the present invention. Figure 3 is a diagram showing a detailed process of teacher characteristic labeling according to one embodiment of the present invention. FIG. 4 is a diagram illustrating a collaborative filtering-based matching process according to an embodiment of the present invention. FIG. 5 is a diagram illustrating a matching reason generation process according to an embodiment of the present invention. FIG. 6 is a diagram showing a matching result provision screen according to an embodiment of the present invention. FIG. 7 is a diagram showing a computer system according to one embodiment of the present invention. Specific details for implementing the invention

[0018] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims.

[0019] The terms used in this specification are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more. Although terms such as "first," "second," etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Therefore, the first component mentioned below may be the second component within the technical scope of the invention.

[0020] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0021] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to facilitate the description of the relationship between one component and other components as illustrated in the drawings. Spatially relative terms should be understood as encompassing different orientations of components during use or operation, in addition to the orientations depicted in the drawings. For example, if a component depicted in a drawing is inverted, a component described as "below" or "beneath" of another component may be placed "above" of that component. Therefore, the exemplary term "below" may encompass both the lower and upper directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation.

[0022] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0023] FIG. 1 is a diagram showing a system configuration according to one embodiment of the present invention.

[0024] Referring to FIG. 1, a system according to one embodiment of the present invention may include a teacher-student matching and analysis system (110), a teacher terminal (121), and a student terminal (122).

[0025] The teacher-student matching and analysis system (110) is a core component that communicates with teacher terminals (121) and student terminals (122) via a network and provides teacher-student matching and analysis results. The teacher-student matching and analysis system (110) may include a data collection module (111), a data preprocessing module (112), a vector generation module (113), a matching analysis module (114), an output control module (115), and a database (116).

[0026] The data collection module (111) collects teacher activity data including teacher's subject, lecture information, feedback data and response history data, and student activity data including student's course history and lecture participation data.

[0027] As an optional embodiment, the data collection module (111) may collect feedback text provided by the teacher, question and answer times, lecture progress information, etc., from the teacher terminal (121). Additionally, it may collect the student's course attendance history, lecture participation level, assignment submission history, etc., from the student terminal (122).

[0028] As an optional embodiment, the data collection module (111) may collect data periodically or in real time, and the collected data is stored in a database (116).

[0029] The data preprocessing module (112) labels teacher characteristics including the teacher's strengths and feedback style based on the collected teacher activity data, and labels student characteristics including the student's learning tendencies and preferred feedback style based on the collected student activity data.

[0030] As an optional embodiment, the data preprocessing module (112) can determine the quality of the feedback by analyzing at least one of the teacher's feedback text, the length of the feedback, and the student satisfaction based on the feedback data, determine the response speed by analyzing the time difference between the time of question registration and the time of answer provision based on the response history data, and determine the degree of improvement in participation by calculating the amount of change in student participation between the start time and the end time of the lecture course based on the lecture participation data.

[0031] As an optional embodiment, the data preprocessing module (112) can classify the teacher's feedback style using natural language processing technology. For example, the feedback style can be labeled as "detailed descriptive," "concise summary," "question-inducing," "encouragement-centered," etc.

[0032] As an optional embodiment, the data preprocessing module (112) can label learning tendencies by analyzing the student's past course history and participation patterns. For example, learning tendencies can be classified as "prefers systematic learning," "prefers self-directed learning," "meticulous tendencies," "prefers quick feedback," etc.

[0033] As an optional embodiment, the data preprocessing module (112) may additionally extract and analyze learning achievement data from the lecture participation data. Learning achievement data is data representing a student's actual learning performance, such as quiz scores, test scores, and homework correct answer rates, and is collected and analyzed separately from the participation data. Through this, not only the degree of student participation in class but also the actual improvement in learning results can be evaluated together.

[0034] The vector generation module (113) generates a teacher vector based on labeled teacher characteristics and generates a student vector based on labeled student characteristics.

[0035] As an optional embodiment, the teacher vector may be composed of a multidimensional vector including a feedback quality score, response speed score, engagement improvement score, strengths trait code, feedback style code, etc. For example, the teacher vector may be expressed as follows: Teacher Vector = [Feedback Quality: 85 points, Response Speed: 90 points, Engagement Improvement: 78 points, Strengths Traits: [Detailed Feedback, Systematic Curriculum], Feedback Style: Detailed Explanatory].

[0036] As an optional embodiment, the teacher vector may further include a learning achievement improvement score. In this case, the teacher vector may be composed of a multidimensional vector including a feedback quality score, response speed score, engagement improvement score, learning achievement improvement score, strengths attribute code, feedback style code, etc. For example, the teacher vector may be expressed as follows: Teacher Vector = [Feedback Quality: 85 points, Response Speed: 90 points, Engagement Improvement: 78 points, Learning Achievement Improvement: 82 points, Strengths Attribute: [Detailed Feedback, Systematic Curriculum], Feedback Style: Detailed Explanatory].

[0037] As an optional embodiment, the student vector may be composed of a multidimensional vector including a learning propensity code, a preferred feedback style code, current engagement, course history, etc. For example, the student vector may be expressed as [Learning propensity: Systematic, Preferred style: Detailed, Current engagement: 65 points, Number of courses taken: 3].

[0038] The matching analysis module (114) calculates the similarity between the teacher vector and the student vector to calculate the teacher-student matching fit score.

[0039] As an optional embodiment, the matching analysis module (114) may use various similarity measurement methods such as cosine similarity, Euclidean distance, and Manhattan distance.

[0040] As an optional embodiment, the matching analysis module (114) may correct the matching suitability score by utilizing a collaborative filtering technique. It may collect characteristic data of teachers selected by other students with similar learning tendencies to the student, derive a teacher characteristic pattern suitable for the student based on this data, and calculate the degree of agreement between the teacher characteristic pattern and the teacher characteristics of the candidate teacher and reflect this in the matching suitability score.

[0041] The output control module (115) provides at least one of the matched teacher information, the matched suitability score, and the matching reason to the student terminal (122) based on the matching suitability score, and provides at least one of the student distribution by preferred feedback style, the list of students with high matching suitability scores, and the teacher characteristic-based branding report to the teacher terminal (121).

[0042] As an optional embodiment, the output control module (115) can analyze the degree of alignment between the teacher's strength characteristics and the student's learning tendencies, and analyze the degree of alignment between the teacher's feedback style and the student's preferred feedback style, convert this into text form, and provide it as a reason for the alignment.

[0043] As an optional embodiment, the output control module (115) may include an indicator of a teacher's learning achievement improvement when generating a teacher characteristic-based branding report. The indicator of learning achievement improvement is an indicator representing the actual improvement in the learning performance of students under the teacher's charge, and is calculated based on changes in the average quiz score, improvement in homework correct answer rate, improvement in test scores, reduction in incorrect answers, etc. For example, it may be expressed in specific figures such as "62% improvement in the average quiz score of students under charge (55 points → 89 points)," "79% increase in the number of homework submissions (28 people → 50 people)," and "33 percentage point increase in the homework correct answer rate (45% → 78%)."

[0044] As an optional embodiment, the branding report may include a teacher competency score. The teacher competency score is a value between 0 and 100 calculated by combining the feedback quality score, response speed score, engagement improvement score, and learning achievement improvement score, and represents the teacher's overall educational competency. For example, the teacher competency score can be calculated using the formula: Teacher Competency Score = (Feedback Quality × 0.25) + (Response Speed ​​× 0.20) + (Engagement Improvement × 0.25) + (Learning Achievement Improvement × 0.30). By assigning the highest weight to learning achievement improvement, the actual educational effect can be evaluated as important.

[0045] As an optional embodiment, the branding report may include teacher ranking information. Teacher ranking is a relative ranking calculated by comparing the teacher competency scores of other teachers on the platform, indicating the top percentage of all teachers. Detailed rankings by subject and region may also be provided. This branding report supports teachers in objectively verifying their educational performance and utilizing it as material for student recruitment and marketing.

[0046] The database (116) stores collected teacher activity data, student activity data, labeled feature information, generated vectors, matching history, matching fit scores, etc.

[0047] The teacher terminal (121) is a device used by a teacher and can be implemented as various types of electronic devices, such as smartphones, tablet PCs, laptops, and desktop computers. The teacher terminal (121) communicates with the teacher-student matching and analysis system (110) via a network, and the teacher can check information on students matched to them, student distribution by preferred feedback style, branding reports, etc.

[0048] The student terminal (122) is a device used by a student and can be implemented as various types of electronic devices such as smartphones, tablet PCs, laptops, and desktop computers. The student terminal (122) communicates with the teacher-student matching and analysis system (110) via a network, and the student can check information about teachers recommended to them, matching suitability scores, reasons for matching, etc.

[0049] FIG. 2 is an overall flowchart of a method for providing teacher-student matching and analysis results according to one embodiment of the present invention.

[0050] Referring to FIG. 2, a method for providing teacher-student matching and analysis results according to one embodiment of the present invention consists of a five-step process.

[0051] First, the teacher-student matching and analysis system (110) collects teacher activity data and student activity data (S210). Teacher activity data includes the teacher's subject, lecture information, feedback data, and response history data, and student activity data includes the student's course enrollment history and lecture participation data.

[0052] As an optional embodiment, teacher activity data may include feedback text written by the teacher, the time of response to student questions, lecture progress records, student satisfaction survey results, etc. Student activity data may include a list of previously taken courses, participation levels in each course (attendance rate, assignment submission rate, question frequency, etc.), course completion status, etc.

[0053] As an optional embodiment, data collection may be collected in real time from the teacher terminal (121) and the student terminal (122), or collected in a batch processing manner at preset intervals (e.g., daily, weekly).

[0054] Next, the teacher-student matching and analysis system (110) performs teacher characteristic labeling and student characteristic labeling (S220). Based on teacher activity data, teacher characteristics including the teacher's strength characteristics and feedback style are labeled, and based on student activity data, student characteristics including the student's learning tendency and preferred feedback style are labeled.

[0055] As an optional embodiment, the teacher characteristic labeling process is described in detail in FIG. 3 and includes detailed steps such as determining feedback quality, determining response speed, and determining the degree of improvement in participation.

[0056] As an optional embodiment, the student characteristic labeling process includes a step of analyzing a student's past course history to identify preferred lecture styles, learning patterns, participation tendencies, etc. For example, a student who primarily takes lectures from a teacher who provides detailed feedback may be labeled as "prefers detailed explanations."

[0057] Next, the teacher-student matching and analysis system (110) generates a teacher vector and a student vector (S230). A teacher vector is generated based on labeled teacher characteristics, and a student vector is generated based on labeled student characteristics.

[0058] As an optional embodiment, qualitative characteristics (e.g., feedback style) may be quantified using one-hot encoding or embedding during the vector generation process. Quantitative characteristics (e.g., feedback quality score) may be normalized and included in the vector.

[0059] As an optional embodiment, the teacher vector and the student vector are designed to be represented in the same dimensional space so that similarity can be calculated thereafter.

[0060] Next, the teacher-student matching and analysis system (110) calculates a matching fit score between the teacher and the student (S240). The matching fit score is calculated by calculating the similarity between the teacher vector and the student vector.

[0061] As an optional embodiment, a collaborative filtering technique may be utilized in the process of calculating the matching fit score, which is described in detail in FIG. 4. The matching fit score can be corrected by analyzing the teacher patterns selected by other students with similar learning tendencies.

[0062] As an optional embodiment, the matching fit score is calculated as a value between 0 and 100, and a higher score indicates a higher fit between the teacher and the student.

[0063] Finally, the teacher-student matching and analysis system (110) provides matching and analysis results (S250). Based on the matching suitability score, at least one of the matched teacher information, the matching suitability score, and the reason for matching is provided to the student terminal (122), and at least one of the student distribution by preferred feedback style, the list of students with high matching suitability scores, and the teacher characteristic-based branding report is provided to the teacher terminal (121).

[0064] As an optional embodiment, the matching reason provided to the student terminal (122) is described in detail in FIGS. 5 and 6, and the results of analyzing the degree of alignment between the teacher's strength characteristics and the student's learning tendency, and the degree of alignment between the teacher's feedback style and the student's preferred feedback style, are provided in text form.

[0065] As an optional embodiment, the branding report provided to the teacher terminal (121) may include a chart visualizing the teacher's strength characteristics, a graph of student distribution by preferred feedback style, a list of students with high matching suitability scores, etc.

[0066] As an optional embodiment, the branding report provided to the teacher terminal (121) may further include learning achievement improvement indicators, teacher competency scores, teacher ranking information, etc. The learning achievement improvement indicators represent changes in specific learning performance of the students in charge and may be provided in the form of, for example, "Quiz average 55 points → 89 points (62% improvement)," "Number of homework submissions 28 → 50 (79% increase)," "Homework correct answer rate 45% → 78% (33%p increase)." The teacher competency score is displayed as a value between 0 and 100 points and is a value that combines feedback quality, response speed, improvement in engagement, and improvement in learning achievement. The teacher ranking indicates what percentage of all teachers the teacher ranks in, and detailed rankings by subject and region may also be provided. This branding report supports teachers in objectively verifying their educational performance and utilizing it for student recruitment and career management by saving or sharing it in the form of a portfolio.

[0067] Figure 3 is a diagram showing a detailed process of teacher characteristic labeling according to one embodiment of the present invention.

[0068] Referring to FIG. 3, the teacher characteristic labeling process includes detailed steps of feedback quality analysis (S310), response speed analysis (S320), and participation improvement analysis (S330).

[0069] In the feedback quality analysis (S310) step, the feedback quality is determined by analyzing at least one of the teacher's feedback text, feedback length, and student satisfaction based on the feedback data.

[0070] As an optional embodiment, feedback text analysis may be performed using natural language processing technology. A quality score may be calculated by evaluating the specificity, clarity, and inclusion of constructive suggestions of the feedback.

[0071] As an optional embodiment, the feedback length may measure the amount of meaningful content rather than simply the number of characters. For example, the actual content length after removing stop words may be measured.

[0072] As an optional embodiment, student satisfaction may be calculated based on star ratings, likes, or survey responses provided by students regarding feedback. For example, a teacher who receives an average of 4.5 points or higher on a 5-point scale may receive a high feedback quality score.

[0073] As an optional embodiment, the feedback quality score may be calculated by weighting the three factors above. For example, the feedback quality score may be calculated using the formula: Feedback Quality Score = (Text Quality × 0.5) + (Appropriateness of Feedback Length × 0.2) + (Student Satisfaction × 0.3) and yield a value between 0 and 100 points.

[0074] In the response speed analysis (S320) step, the response speed is determined by analyzing the time difference between the question registration time and the answer provision time based on the above response history data.

[0075] As an optional embodiment, the response speed score may be calculated based on the average response time. For example, it may be scored as 100 points for a response within 24 hours, 80 points for a response within 48 hours, 60 points for a response within 72 hours, and 40 points for a response longer than that.

[0076] As an optional embodiment, the urgency or difficulty of the question may be considered when analyzing response speed. For non-urgent questions, the penalty may be small even if the response time is somewhat long.

[0077] As an optional embodiment, the response speed score may be calculated based on the average response time over a recent period (e.g., the last three months) to reflect the teacher's current response capability.

[0078] In the participation improvement analysis (S330) step, the change in student participation between the start and end times of the lecture course is calculated based on the above lecture participation data to determine the degree of participation improvement.

[0079] As an optional embodiment, student participation may be measured by combining attendance rate, assignment submission rate, question frequency, and interaction frequency during class. For example, participation may be calculated using the formula: participation = (attendance rate × 0.3) + (assignment submission rate × 0.3) + (question frequency × 0.2) + (interaction frequency × 0.2).

[0080] As an optional embodiment, the degree of improvement in participation is calculated by comparing the average student participation at the start of the lecture course with the average student participation at the end. For example, if the participation at the start is 60 points and the participation at the end is 80 points, the improvement is 20 points, which can be evaluated as an improvement of approximately 33% when converted to a percentage.

[0081] As an optional embodiment, the participation improvement score can be converted into a value between 0 and 100 points by normalizing the degree of improvement. For example, it can be scored as 100 points for an improvement of 30% or more, 80 points for an improvement of 20%, 60 points for an improvement of 10%, 50 points for no change, and 40 points or less for a decrease.

[0082] As an optional embodiment, the average value of the degree of participation improvement measured across multiple lecture courses can be calculated as the final participation improvement score.

[0083] The feedback quality score, response speed score, and engagement improvement score calculated in this way are used as quantitative indicators of teacher characteristics and are subsequently included when generating teacher vectors.

[0084] In the learning achievement improvement analysis (S340) step, the change in the student's learning achievement is calculated from the above lecture participation data to determine the degree of improvement in learning achievement. Learning achievement is a separate indicator distinct from student participation and represents the student's actual learning results.

[0085] Learning achievement can be measured based on average quiz scores, test scores, homework accuracy rates, error reduction rates, and average score increase rates.

[0086] As an optional embodiment, the change in learning achievement can be calculated by comparing learning performance data at the start and end of the lecture. For example, if the average quiz score is 55 points at the start of the lecture and 89 points at the end, the score improvement is 34 points, which can be evaluated as an improvement of approximately 62% when converted into a percentage.

[0087] As another example, if the homework correct answer rate increased from 45% to 78%, it can be evaluated as an improvement of 33 percentage points, and if the number of homework submissions increased from 28 to 50, it can be evaluated as an increase in the number of submissions of 79%.

[0088] As an optional embodiment, the change in learning achievement can be used as an indicator to evaluate the teacher's educational effectiveness along with the degree of improvement in participation. A teacher may possess both the ability to induce student participation (improvement in participation) and the ability to improve actual learning outcomes (improvement in learning achievement), and the teacher's overall educational effectiveness can be calculated by combining these two indicators. For example, educational effectiveness can be calculated using the formula: Educational Effectiveness = (Improvement in Participation Score × 0.4) + (Improvement in Learning Achievement Score × 0.6).

[0089] As an optional embodiment, the average values ​​of the degree of improvement in participation and learning achievement measured across multiple lecture courses can be calculated as the final score. The feedback quality, response speed, degree of improvement in participation, and degree of improvement in learning achievement calculated in this way are utilized as quantitative indicators of teacher characteristics and are subsequently included when generating teacher vectors. In particular, the degree of improvement in learning achievement serves as a key indicator representing the actual educational effectiveness of a teacher and can be significantly utilized for teacher competency evaluation and the creation of branding materials.

[0090] FIG. 4 is a diagram illustrating a collaborative filtering-based matching process according to an embodiment of the present invention.

[0091] Referring to FIG. 4, the collaborative filtering-based matching process consists of the steps of searching for similar students centered on student A (410), deriving preferred teacher patterns, determining the degree of agreement with candidate teachers, and calculating the final matching suitability score.

[0092] First, when the learning tendency of target student A (410) is identified as “systematically,” the system searches for other students with similar learning tendencies.

[0093] As an optional embodiment, in the similar student search step, the similarity between student vectors is calculated to extract the students most similar to the target student. For example, students B, C, and D with a learning style of "systematic" can be searched.

[0094] As an optional embodiment, when calculating similarity, various characteristics such as current level of engagement and preferred feedback style, as well as learning propensity, may be comprehensively considered. For example, students with a cosine similarity of 0.8 or higher may be classified as similar students.

[0095] Next, characteristic data of teachers previously selected by similar students is collected. As shown in Figure 4, the search results for similar students show that Student B (systematic) selected Teacher X, Student C (systematic) selected Teacher Y, and Student D (systematic) selected Teacher X.

[0096] As an optional example, the frequency with which each teacher is selected is tallied. For example, Teacher X was selected 2 times, and Teacher Y was selected 1 time. This means that students with a systematic learning disposition prefer Teacher X more.

[0097] Next, the collected teacher characteristic data is analyzed to derive preferred teacher patterns. As shown in Figure 4, Teacher X was selected twice, and the characteristics of Teacher X are analyzed as "detailed feedback" and "systematic curriculum."

[0098] As an optional embodiment, in the step of deriving preferred teacher patterns, common characteristics of high-frequency teachers are extracted. For example, by analyzing the common characteristics of Teacher X and Teacher Y, it can be derived that "detailed feedback" and "systematic curriculum" are teacher patterns preferred by systematic students.

[0099] As an optional embodiment, the teacher characteristic pattern may be represented in vector form. For example, it may be expressed as pattern vector = [Detailed Feedback: High, Systematic Curriculum: High, Fast Response: Medium].

[0100] Next, the degree of agreement between the characteristics of the candidate teacher and the derived teacher characteristic pattern is determined. As illustrated in FIG. 4, Teacher Z (420) has both "detailed feedback" and "systematic curriculum" characteristics, showing a high degree of agreement with the derived pattern.

[0101] As an optional embodiment, the degree of agreement is calculated by calculating the similarity between the characteristic vector and the pattern vector of teacher Z (420). For example, if the result of calculating the cosine similarity yields a high similarity of 0.95, the degree of agreement score may be evaluated as 95 points.

[0102] As an optional embodiment, the importance of each characteristic may be reflected as a weight when calculating the agreement. For example, if the "detailed feedback" characteristic is determined to be more important, a higher weight may be assigned to that characteristic.

[0103] Finally, the calculated agreement is reflected in the existing matching fit score. As shown in Figure 4, the matching fit between student A and teacher Z is ultimately calculated to be 95 points.

[0104] As an optional embodiment, the match score through collaborative filtering may be added to the base similarity score or weighted averaged to produce a final matching fit score. For example, the final score may be calculated using the formula: Final score = (Base similarity × 0.6) + (Collaborative filtering match × 0.4).

[0105] As an optional embodiment, if the number of similar students is insufficient (e.g., fewer than 5), only the basic similarity score may be used without applying collaborative filtering correction. This is to prevent bias caused by a small amount of data.

[0106] Through this collaborative filtering-based matching process, the accuracy of matching can be improved by going beyond simply comparing the characteristics of teachers and students and reflecting the teacher patterns actually preferred by similar students.

[0107] FIG. 5 is a diagram illustrating a matching reason generation process according to an embodiment of the present invention.

[0108] Referring to Fig. 5, the matching reason generation process consists of three stages: degree of alignment analysis, degree of agreement analysis, and matching reason generation.

[0109] First, in the alignment analysis step, the degree of alignment between the teacher's strength characteristics and the student's learning tendencies is analyzed. As shown in Figure 5, the alignment between "detailed feedback" and "meticulousness" is calculated as 92 points.

[0110] As an optional embodiment, a degree of match analysis evaluates how well a teacher's strengths match a student's learning style. For example, a teacher with "detailed feedback" as a strength may show a high degree of match to a student with a "meticulous" learning style.

[0111] As an optional embodiment, the degree of match can be calculated through a predefined match matrix. For example, the combination [Teacher Strength: Detailed Feedback] - [Student Disposition: Meticulous] has a match coefficient of 0.92 in the matrix, which is converted to a score of 92 out of 100.

[0112] As an optional embodiment, if there are multiple strength characteristics and learning tendencies, the degree of alignment of each combination can be calculated and averaged or weighted to calculate the final degree of alignment.

[0113] Next, in the agreement analysis step, the degree of agreement between the teacher's feedback style and the student's preferred feedback style is analyzed. As shown in Figure 5, the agreement between "systematic" and "detailed explanation" is calculated to be 88 points.

[0114] As an optional embodiment, a degree of agreement analysis evaluates how well the feedback style provided by a teacher aligns with the feedback style preferred by a student. For example, a teacher with a "systematic" feedback style may show a high degree of agreement with a student who prefers "detailed explanations."

[0115] As an optional embodiment, the degree of agreement can be calculated through a feedback style similarity matrix. For example, the combination [Teacher Style: Systematic] - [Student Preference: Detailed] has an agreement coefficient of 0.88 in the matrix, which is 88 out of 100 points.

[0116] As an optional embodiment, feedback styles may be classified into "detailed descriptive," "concise summary," "question-inducing," "encouragement-centered," etc., and similarity or compatibility between each style may be predefined in a matrix.

[0117] Finally, in the matching reason generation step, the calculated degree of alignment and degree of agreement are converted into text form to generate a matching reason. As shown in Fig. 5, the final matching reason is generated as "This teacher provides detailed feedback suitable for meticulous students and prefers systematic lecture delivery."

[0118] As an optional embodiment, the matching reason text may use a template-based generation method. For example, text can be generated by inputting the analysis results into a template such as, "This teacher provides [teacher strengths] suitable for students with [student orientation] and prefers [teacher style] teaching methods."

[0119] As an optional embodiment, Natural Language Generation (NLG) technology may be utilized when generating matching reasons. By generating natural sentences that fit the context rather than standardized templates, the user experience can be improved.

[0120] As an optional embodiment, when both the degree of match and the degree of agreement are high (e.g., both 85 points or higher), an emphasis expression such as "very suitable" may be added to the reason for the match. Conversely, when the score is at an intermediate level (e.g., 70 to 85 points), a neutral expression such as "suitable" may be used.

[0121] As an optional embodiment, quantitative indicators may also be provided for the reason for matching. For example, reliability can be increased by adding information such as "This teacher received an average satisfaction score of 85 from similar students in the past."

[0122] Through this matching reason generation process, students receive not only a score but also a specific and easy-to-understand explanation of why the teacher is suitable for them, which improves the reliability and satisfaction with the matching results.

[0123] FIG. 6 is a diagram showing a matching result provision screen according to an embodiment of the present invention.

[0124] Referring to FIG. 6, the screen (610) of the student terminal displays recommended teacher information, a matching score, and a matching reason in an integrated manner. At the top of the screen, basic information of the matched teacher is displayed, such as "Recommended Teacher: Teacher Kim OO," and below that, a visualized matching suitability score is displayed, such as "Matching Score: 95 points."

[0125] As an optional embodiment, the matching reason area displays the matching reason in text form generated in FIG. 5. For example, a description such as "This teacher provides detailed feedback suitable for meticulous students and prefers systematic lecture delivery" is provided.

[0126] As an optional embodiment, a "Course Registration" button is placed at the bottom of the screen so that the student can proceed with course registration immediately after checking the matching results.

[0127] As an optional embodiment, the matching reason area may be implemented in a foldable form so that students who want a simple view can check only the score, and students who want a detailed explanation can unfold the matching reason to check it.

[0128] FIG. 7 is a diagram showing a computer system according to one embodiment of the present invention.

[0129] A method for providing teacher-student matching and analysis results according to one embodiment of the present invention can be implemented in a computer system (1000), such as a computer-readable recording medium.

[0130] Referring to FIG. 7, a computer system (1000) may include one or more processors (1010), memory (1030), user interface input device (1040), user interface output device (1050), and storage (1060) that communicate with each other via a bus (1020). Additionally, the computer system (1000) may further include a network interface (1070) connected to a network (1080). The processor (1010) may be a central processing unit or a semiconductor device that executes processing instructions stored in memory (1030) or storage (1060). Memory (1030) and storage (1060) may be various forms of volatile or non-volatile storage media. For example, memory may include ROM (1031) or RAM (1032).

[0131] The specific embodiments described in this invention are examples and do not limit the scope of the invention in any way. For the sake of brevity of the specification, descriptions of prior electronic configurations, control systems, software, and other functional aspects of said systems may be omitted. Additionally, the connections of lines or connecting members between components shown in the drawings are illustrative of functional connections and / or physical or circuit connections, and may be replaced or additionally represented as various functional connections, physical connections, or circuit connections in actual devices. Furthermore, unless specifically stated as "essential," "importantly," etc., a component may not be strictly necessary for the application of the invention.

[0132] Accordingly, the scope of the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention.

[0133] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0134] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. Explanation of the symbols

[0135] 110: Teacher-Student Matching and Analysis System 111: Data Collection Module 112: Data Preprocessing Module 113: Vector Generation Module 114: Matching Analysis Module 115: Output Control Module 116: Database 121: Teacher Terminal 122: Student Terminal 1000: Computer System 1010: Processor 1020: Bus 1030: Memory 1031: ROM 1032: RAM 1040: User interface input device 1050: User interface output device 1060: Storage 1070: Network Interface 1080: Network

Claims

Claim 1 A method for providing teacher-student matching and analysis results by an information processing device comprises: collecting teacher activity data including a teacher's subject, lecture information, feedback data, and response history data, and student activity data including a student's course enrollment history and lecture participation data; labeling teacher characteristics including a teacher's strength characteristics and feedback style based on the teacher activity data, and labeling student characteristics including a student's learning propensity and preferred feedback style based on the student activity data; generating a teacher vector based on the teacher characteristics and generating a student vector based on the student characteristics; and calculating a teacher-student matching suitability score by calculating the similarity between the teacher vector and the student vector. The method includes the step of providing at least one of teacher information matched to a student terminal, a matching suitability score, and a reason for matching based on the matching suitability score, and providing to the teacher terminal a student distribution by preferred feedback style, a list of students with high matching suitability scores, and a branding report based on teacher characteristics; the step of labeling teacher characteristics includes: determining feedback quality by analyzing at least one of the teacher's feedback text, feedback length, and student satisfaction based on the feedback data; determining response speed by analyzing the time difference between the time of question registration and the time of answer provision based on the response history data; determining the degree of improvement in participation by calculating the amount of change in student participation between the start and end times of the lecture course based on the lecture participation data; and determining the degree of improvement in learning achievement by calculating the amount of change in student learning achievement based on the learning achievement data extracted from the lecture participation data; and the step of calculating the matching suitability score includes: collecting characteristic data of teachers selected by other students with similar learning tendencies to the student; and deriving a teacher characteristic pattern suitable for the student based on the characteristic data.A method for providing teacher-student matching and analysis results, comprising the step of calculating the degree of agreement between the teacher characteristic pattern and the teacher characteristics of the teacher and reflecting it in the matching suitability score. Claim 2 delete Claim 3 delete Claim 4 A method for providing teacher-student matching and analysis results according to claim 1, wherein the step of providing the matching reason comprises: a step of analyzing the degree of alignment between the strength characteristics of the teacher and the learning tendencies of the student; a step of analyzing the degree of agreement between the feedback style of the teacher and the preferred feedback style of the student; and a step of converting the degree of alignment and the degree of agreement into text form and providing them as the matching reason. Claim 5 A memory on which at least one program is recorded; and a processor for executing said program, wherein the program comprises: collecting teacher activity data including a teacher’s subject, lecture information, feedback data, and response history data, and student activity data including a student’s course history and lecture participation data; labeling teacher characteristics including a teacher’s strengths and feedback style based on said teacher activity data, and labeling student characteristics including a student’s learning propensity and preferred feedback style based on said student activity data; generating a teacher vector based on said teacher characteristics and generating a student vector based on said student characteristics; and calculating a similarity between said teacher vector and said student vector to calculate a teacher-student matching fit score. The method includes instructions for performing the step of providing at least one of teacher information matched to a student terminal, a matching suitability score, and a matching reason based on the above matching suitability score, and providing to a teacher terminal a student distribution by preferred feedback style, a list of students with high matching suitability scores, and a teacher characteristic-based branding report, wherein the step of labeling the teacher characteristics includes: determining feedback quality by analyzing at least one of the teacher's feedback text, feedback length, and student satisfaction based on the above feedback data; determining response speed by analyzing the time difference between the question registration time and the answer provision time based on the above response history data; determining the degree of improvement in participation by calculating the amount of change in student participation between the start time and the end time of the lecture course based on the above lecture participation data; and determining the degree of improvement in learning achievement by calculating the amount of change in student learning achievement based on the above learning achievement data extracted from the above lecture participation data, wherein the step of calculating the matching suitability score includes: collecting characteristic data of teachers selected by other students who have similar learning tendencies to the student.A teacher-student matching and analysis result providing device comprising: a step of deriving a teacher characteristic pattern suitable for the student based on the above characteristic data; and a step of calculating the degree of agreement between the teacher characteristic pattern and the teacher characteristics of the teacher and reflecting it in the matching suitability score.

Images