A pediatrics education and teaching device and method for medical treatment
By calculating students' stage weights and trend coefficients and constructing personalized data division, the problem of ignoring phased learning habits in traditional teaching methods is solved, and high-quality personalized teaching in pediatric education is achieved.
Patent Information
- Application Number
- CN202411067495.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-06
AI Technical Summary
In the medical big data environment, traditional pediatric education teaching methods have failed to effectively achieve targeted teaching, ignoring students' phased learning habits and learning time characteristics, resulting in poor adjustment of teaching resources, affecting the accuracy of personalized education sex.
By obtaining students' test score data, the CRITIC algorithm is used to calculate the stage weight and trend coefficients, and two-dimensional coordinates are constructed based on the relative difference coefficients to divide students' personalized data, thereby realizing targeted teaching resource allocation.
It improves the accuracy of accurate division of teaching information data, realizes the accuracy of personalized teaching characteristics analysis and targeted teaching effect, and improves the teaching quality of pediatric education.
Smart Images

Figure CN118608343B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of teaching methods, and in particular to a pediatric internal medicine education and teaching device and method for medical treatment. Background Art
[0002] With the continuous development of big data analysis technology, the research field of pediatric education and teaching methods has gradually been combined with big data analysis technology, involving the combined use of various innovative and traditional teaching methods to improve the professional capabilities of medical students and doctors. At present, pediatric education and teaching for medical treatment have begun to be combined with medical big data. During the teaching process, the latest pediatric medical information data and advanced technology research information used in pediatric medical treatment can be provided to help students understand and learn pediatric medical related information.
[0003] However, in the environment of medical big data, targeted teaching methods for pediatrics education and teaching used in medical treatment have not been achieved with good results. The traditional teaching data feature extraction method is used to analyze the learning characteristics of different teaching objects, which ignores the students' stage-by-stage learning habits and personalized learning characteristics such as the time to accept teaching content. This leads to poor results in targeted teaching methods and teaching resource adjustments for students based on medical data, affecting the accuracy of targeted teaching resource adjustments for pediatrics education for students based on the learning characteristics reflected in the students' teaching data, and reducing the effect of personalized pediatrics education and teaching achieved through the analysis of teaching information data. Summary of the invention
[0004] In order to solve the above technical problems, the purpose of this application is to provide a pediatric internal medicine education and teaching device and method for medical treatment. The technical solutions adopted are as follows:
[0005] The present application embodiment provides a pediatric internal medicine education and teaching method for medical treatment, the method comprising the following steps:
[0006] Obtain the test score data of each student in all subjects at different times during the pediatrics education and teaching process;
[0007] The CRITIC algorithm is used to obtain the weight corresponding to the test score data of each subject of each student in the same time period. The weights of all subjects constitute the stage weight sequence of each student in the same time period. According to the distance between each student in each time period and the stage weight sequence of other time periods, and the change trend of all the distances of each student in each time period, the stage trend coefficient of each student in each time period is obtained;
[0008] The weight of each student's test score data in each subject at all times is recorded as the long-term weight. The long-term weights of all subjects of each student constitute the long-term weight sequence of each student. Based on the difference between the periodic trend coefficients of each student and other students in all time periods, and the difference between each student and other students' long-term weight sequences, the relative difference coefficient of each student is determined;
[0009] By using the relative difference coefficient of each student and combining the test score data of each student in each subject at different times, a two-dimensional coordinate corresponding to each student is constructed to divide all students;
[0010] Based on the division results, targeted education and teaching will be provided for pediatrics used in medical treatment.
[0011] Preferably, the process of obtaining the phased trend coefficient of each student in each time period is as follows:
[0012] Analyze the distance between each student's stage weight sequence in each time period and other time periods, and record it as the stage weight difference of each student in each time period;
[0013] The trend statistics of all the stage weight differences of each student in each time period are taken as the stage trend coefficient of each student in each time period.
[0014] Preferably, the process of determining the relative coefficient of difference of each student is as follows:
[0015] Based on the difference between each student and other students' period trend coefficients in each time period, determine the period difference of each student;
[0016] Determine long-term differences among students based on how they compare to other students in all subjects over all time periods;
[0017] The relative coefficient of difference of each student is determined based on the periodic differences and long-term differences between each student and all other students.
[0018] Preferably, the process of determining the stage differences of each student is as follows:
[0019] The phase trend coefficients of all time periods of each student constitute the phase trend sequence of each student. The distance between each student and the phase trend sequence of other students is analyzed as the phase difference of each student.
[0020] Preferably, the process of determining the long-term differences of each student is:
[0021] Analyze the distance between each student and other students' long-term weight sequences, and record it as the long-term difference of each student.
[0022] Preferably, the relative difference coefficient of each student is the average of the product of the stage difference and the long-term difference between each student and all other students.
[0023] Preferably, the process of constructing the two-dimensional coordinates corresponding to each student is:
[0024] The sum of the test score data of all subjects of each student at each time is recorded as the vertical mapping value, the discrete degree of the vertical mapping value of each student at all times is used as the horizontal coordinate of each student, and the relative difference coefficient of each student is used as the vertical coordinate of each student, forming the two-dimensional coordinate corresponding to each student.
[0025] Preferably, each personalized data set is a set consisting of test score data of all students in each cluster obtained by clustering the two-dimensional coordinates of all students.
[0026] Preferably, the targeted education and teaching of pediatrics for medical treatment based on each personalized data set further includes:
[0027] The test score data of each subject in each personalized data set at different times are fitted to obtain the data change curve of each subject in each personalized data set, so as to configure corresponding teaching resources according to the performance of each category of students in different subjects.
[0028] The present application embodiment also provides a pediatrics education and teaching device for medical treatment, the pediatrics education and teaching device comprising:
[0029] The teaching data collection module is used to obtain the test score data of each student in all subjects at different times during the pediatrics education and teaching process;
[0030] The teaching characteristic analysis module is used to obtain the periodic trend coefficient of each student in each time period according to the changes and differences in the test score data of each student in each subject in different time periods; determine the relative difference coefficient of each student based on the difference between the periodic trend coefficient of each student and other students in all time periods, and the long-term difference between the subject test score data of each student and other students in all time periods; construct the two-dimensional coordinates corresponding to each student through the relative difference coefficient of each student, combined with the test score data of each student in each subject at different times, so as to divide all students;
[0031] The targeted teaching adjustment module is used to carry out targeted education and teaching of pediatrics used for medical treatment according to the division results.
[0032] From the above, it can be seen that the pediatric internal medicine education and teaching device and method provided in this application for medical treatment have at least the following beneficial effects:
[0033] This application takes into account that in the implementation process of traditional personalized teaching, the classification feature analysis of the teaching information content of different students does not take into account the influence of different students' teaching information data on their stage learning habits and learning efficiency at different times, resulting in inaccurate division of teaching information data of students with similar learning characteristics, and then reducing the learning feature analysis of different students based on the division results of teaching information. There is still a large error. In response to this situation, this application collects teaching information data of different students, and conducts a relative analysis of the stage-by-stage learning feature differences and stage-by-stage learning efficiency differences based on the teaching information data of each student, and extracts parameters that accurately represent the stage-by-stage learning characteristics of each student in combination with the comparison results of the stage-by-stage characteristics of different students, thereby achieving accurate division of the teaching information data of different students in the teaching process of pediatrics. The beneficial effect is that compared with the traditional analysis method, the combination of stage analysis characteristics improves the accuracy of the division of teaching information data of different students, thereby improving the accuracy of personalized learning feature analysis in the teaching process of pediatrics, thereby achieving effective and targeted pediatrics teaching for medical treatment. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0035] Figure 1 A flowchart of the steps of a pediatric internal medicine education and teaching method for medical treatment provided in this application;
[0036] Figure 2 Schematic diagram of the process of constructing the relative coefficient of difference of each student provided for this application;
[0037] Figure 3 A block diagram of a pediatric education and teaching device for medical treatment provided in this application. DETAILED DESCRIPTION
[0038] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features and effects of a pediatric internal medicine education and teaching device and method for medical treatment proposed in the present application. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0039] Unless otherwise specified and limited, terms such as "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application.
[0040] The specific scheme of a pediatric internal medicine education and teaching device and method for medical treatment provided by the present application is described in detail below with reference to the accompanying drawings.
[0041] See also Figure 1 , which shows a flowchart of a method for pediatric internal medicine education and teaching for medical treatment provided by an embodiment of the present application, the method comprising the following steps:
[0042] Step 1: Obtain the test score data of each student in all subjects at different times during the pediatrics education and teaching process.
[0043] Data collection is performed on the test score data of all subjects of each student at different times during the pediatrics education and teaching process. In this embodiment, the test score data of each student in each subject at different times is obtained in the pediatrics teaching system as the teaching information data of each student, and the sequence composed of the test score data of all subjects of each student at each time is used as the teaching information data sequence. For example, the teaching information data sequence of any student at any time can be ,in Respectively represent the 1st, 2nd, The test score data of each subject; the teaching information data sequence of each student at each time is regarded as a teaching information student, and the sequence of all teaching information students corresponding to each student in ascending time order is regarded as a teaching feature sequence. For example, the teaching feature sequence of any student can be ,in Respectively represent the 1st, 2nd, A sequence of teaching information data corresponding to a time period.
[0044] Further, a set of corresponding teaching feature sequences of all students is taken as a teaching information data set; and in one embodiment of the present application, the number of students for which teaching information data is obtained is (The value in this embodiment is 1000), the implementer can determine the data volume according to the number of students in the current historical teaching records.
[0045] At this point, a teaching information data set for pediatric internal medicine teaching for medical treatment has been acquired.
[0046] Step 2: According to the changes and differences in the test score data of each student in each subject in different time periods, obtain the stage trend coefficient of each student in each time period.
[0047] Usually, in the process of pediatric education and teaching, the analysis of different students' learning characteristics is based on the overall trend of comprehensive scores or scores in different subjects and whether the scores meet the standards. The judgment of the similarity of learning characteristics between different students based on the analysis of overall characteristics ignores the influence of differences in stage-by-stage learning habits and the length of time it takes to receive teaching information content in the actual teaching and learning process, resulting in a large deviation in the division of students' teaching data, affecting the accuracy of the analysis of personalized learning characteristics of different students.
[0048] Therefore, this application obtains the teaching information data of different students in the historical teaching record data, and on the basis of combining the changes in the overall teaching information data of each student, considers the differences in learning characteristics at different stages and the differences in learning efficiency of different students for teaching content, and accurately divides the student teaching data of pediatrics teaching used for medical purposes, thereby improving the accuracy of personalized information feature extraction in the pediatrics education and teaching process, and achieving high-quality targeted teaching content push.
[0049] For ease of description, in this embodiment, all teaching information data sequences of each sample are formed into a matrix for analysis. Specifically, for each student in the teaching information data set, each teaching information data sequence in the teaching feature sequence of each student is used as a column element in the matrix, and the matrix composed of all teaching information data sequences in the teaching feature sequence of each student is used as the characteristic matrix of the stage analysis of each student. The relative difference coefficient is constructed according to the relative change difference of the characteristic matrix of the stage analysis in different time periods. The relative difference coefficient reflects the stage learning characteristics and learning efficiency differences of the teaching information data of different students. The specific calculation and analysis process is as follows:
[0050] Furthermore, to facilitate analysis and expression, corresponding rectangular sliding windows are set for different time periods in this embodiment, and all corresponding times in the window correspond to one time period. For the test score data of each subject of each student in each time period, the CRITIC algorithm is used to obtain the weight corresponding to the test score data of each subject of the same student in the same time period, and the weights of all subjects constitute the stage weight sequence of the same student.
[0051] In this embodiment, specifically, for the characteristic matrix of the stage analysis corresponding to each student in the teaching information data set, set A rectangular sliding window of size is the number of test subjects for each student at each time, and the sliding step size of the sliding window is ; The data in each sliding window is divided into rows as input, and the CRITIC algorithm is used to obtain the weight of each row of data from top to bottom in each sliding window. The sequence composed of all the weights is used as the stage weight sequence of each student in each sliding window. Each element in the stage weight sequence represents the relative difference in the test score data changes of each subject within a period of time.
[0052] It should be noted that the above rectangular sliding window has a sliding step length of Greater than the number of remaining matrix columns ,Right now , then the step length of the last slide is ; The above-mentioned rectangular sliding window constructed in the matrix can obtain the test score data of different subjects in the same time period. Specifically in other embodiments, on the basis of achieving the purpose of obtaining the test score data of different subjects in the same time period, other methods of division can be adopted. For example, the time interval can be divided, and the test score data of each subject can be divided separately according to the divided time interval, so as to obtain the test score data of different subjects in the same time interval.
[0053] Furthermore, the difference in stage weight sequences between different sliding windows is used to represent the stage-by-stage learning feature deviation of each student in the learning process, as well as the stage-by-stage test data difference caused by the difference in learning efficiency. Specifically, for each rectangular sliding window in the feature matrix, the distance between the stage weight sequences of each student in each rectangular sliding window and other rectangular sliding windows is taken as the stage weight difference of each student in each rectangular sliding window. In this embodiment, Manhattan distance is used, which can be selected by the implementer.
[0054] It should be understood that the greater the difference in stage weights, the greater the possibility that the current stage has significant learning feature differences based on the relative analysis of the current stage with other stages.
[0055] The sequence composed of the stage weight differences between the rectangular sliding window and all other rectangular sliding windows is taken as the stage weight difference sequence. If the learning feature analysis of the current stage is performed, the difference with the learning features of other stages is manifested as smaller contrast features in the adjacent time range, while the learning feature difference in the range with larger time difference is larger, which means that the learning features of the current time period are more likely to be affected by the difference in learning habits. Therefore, the stage weight difference sequence is taken as input, and the Mann-Kendall trend verification algorithm is used to obtain the trend statistics of the stage weight difference sequence, and the trend statistics are used as the stage trend coefficient of each rectangular sliding window.
[0056] It can be understood that the larger the stage trend coefficient is, the more significant the trend difference of the stage characteristics of teaching information data affected by differences in learning habits is based on the relative characteristic analysis of different time periods.
[0057] Step 3: Determine the relative difference coefficient of each student based on the difference between the periodic trend coefficient of each student and other students in all time periods, as well as the long-term difference between the subject test score data of each student and other students in all time periods.
[0058] After the above steps, the phase trend coefficient for phase relative difference analysis is obtained. Further, the phase difference comparison analysis is carried out according to the phase trend coefficient of the teaching information data of different students. The specific calculation and analysis process is as follows:
[0059] For each student in the teaching information data set, the sequence composed of the stage trend coefficients of all rectangular sliding windows corresponding to the student is taken as the stage trend sequence, and the distance between the stage trend sequence corresponding to each student and the stage trend sequence of each other student is calculated. In this embodiment, the Flamenche distance is used. There are many methods for calculating the distance between sequences, such as Euclidean distance, DTW distance, Manhattan distance, etc., which can be selected by the implementer.
[0060] The Flamenche distance between each student's corresponding phase trend sequence and the phase trend sequence of each other student is recorded as the phase difference of each student. ,The greater the stage difference, the greater the relative difference of stage characteristics between different students, that is, the greater the difference of learning characteristics of different students affected by learning habits in different time periods;
[0061] The characteristic matrix of the stage analysis corresponding to each student is divided into rows as input, and the CRITIC algorithm is used to obtain the weight of each row of data from top to bottom in the characteristic matrix. The sequence composed of all weights is used as the long-term weight sequence of each student; for each student in the teaching information data set, the Manhattan distance of the long-term weight sequence corresponding to the student and each other student is used as the long-term difference ,The larger the long-term difference is, the greater the relative difference of the learning characteristics of the long-term teaching information data among different students is, that the greater the difference in the learning characteristics of different students within the overall time range.
[0062] Calculate the relative difference coefficient based on the phased and long-term differences between each student and every other student in the teaching information data set , wherein the relative difference coefficient is positively correlated with the stage difference and the long-term difference, respectively. Specifically, in one embodiment of the present application, the calculation formula of the relative difference coefficient of each student is: ;
[0063] in, Represents the first The relative coefficient of variation among students; , Respectively represent the first The first The phased and long-term differences between students; The number of students who obtain teaching information data; the larger the relative difference coefficient, the more it indicates that through comprehensive analysis of stage-by-stage learning characteristic differences and long-term relative characteristic differences, the current students have significant personalized characteristics of teaching information.
[0064] At this point, the relative difference coefficient is obtained. For a detailed diagram of the relative difference coefficient construction process for each student, please refer to Figure 2 .
[0065] Step 4: Using the relative difference coefficient of each student and combining the test score data of each student in each subject at different times, construct the two-dimensional coordinates corresponding to each student, and divide all students to obtain personalized data sets.
[0066] For each student in the teaching information data set, the characteristic matrix of the stage analysis corresponding to the student is vertically mapped. The specific vertical mapping method is: the sum of all elements in each column of the characteristic matrix is used as the vertical mapping value, the discrete degree of the vertical mapping values corresponding to all columns is used as the horizontal coordinate of each student, and the relative difference coefficient corresponding to each student in the teaching information data set is used as the vertical coordinate for each student to be divided. ;According to the values of the horizontal and vertical coordinates of each student in the teaching information data set, obtain the two-dimensional coordinates corresponding to each student .
[0067] For ease of description, in this embodiment, the sequence of vertical mapping values of all columns of each student's feature matrix is used as the vertical value mapping sequence of each student; the standard deviation of all elements in the vertical value mapping sequence corresponding to each student in the teaching information data set is used as the horizontal coordinate for feature division of each student. It should be noted that the above-mentioned degree of dispersion in this embodiment adopts the standard deviation of the vertical mapping values corresponding to all columns, that is, the standard deviation of the vertical value mapping sequence corresponding to each student. In addition to using the standard deviation to evaluate the degree of dispersion, the implementer can use other methods of evaluating the degree of dispersion of the sequence in the prior art to calculate, and this embodiment does not impose any special restrictions on this.
[0068] All students in the teaching information data set are divided into two-dimensional coordinates corresponding to each student Mapping into a two-dimensional rectangular coordinate system; using the mapping result of the teaching information data set in the two-dimensional rectangular coordinate system as a characteristic data set targeted at pediatric internal medicine teaching for medical treatment.
[0069] Furthermore, the input is the feature data set, and a density peak clustering algorithm is used to obtain the clustering division result of the feature data set to obtain various cluster clusters. The set consisting of the test score data corresponding to all students in each cluster cluster in the cluster division result is used as a personalized data set for pediatric internal medicine teaching.
[0070] Step 5: Provide targeted education and teaching of pediatrics for medical treatment based on each personalized data set.
[0071] All personalized data sets are transmitted to the pediatrics education and teaching device, which includes a teaching data acquisition module, a teaching feature analysis module, and a targeted teaching adjustment module. The feature analysis module performs statistical analysis on each personalized data set based on the obtained personalized data set. Since each personalized data set is a classification set with similar stage-by-stage learning features and similar comprehensive learning features, a statistical analysis is performed on the teaching information data in each personalized data set, and targeted adjustments are made to the pediatrics teaching used for medical treatment based on the statistical analysis results.
[0072] It should be noted that, in one embodiment of the present application, the teaching information data obtained for each student is the test score data of each student in different subjects at different times. Therefore, the statistical results of each personalized data set are as follows: the test score data of each subject in each personalized data set at different times are fitted to obtain the data change curve of each subject in each personalized data set. According to the statistical results, the comprehensive teaching effect of different subjects can be intuitively reflected, so as to configure corresponding teaching resources for the performance of each category of students in different subjects, and adjust the teaching methods and teaching resource configuration in the process of pediatrics education and teaching according to the comprehensive teaching effect. For example, the specific method is to configure teaching resources according to the performance of different categories of students in different subjects, and the teaching intensity can be increased for subjects with large fluctuations in the data change curve, and more education courses can be arranged to maintain the overall stability of the student scores of the subject. The specific configuration of teaching resources is determined by the implementer according to the actual application scenario.
[0073] Based on the same inventive concept as the above method, the embodiment of the present application further provides a pediatric internal medicine education and teaching device for medical treatment, the pediatric internal medicine education and teaching device comprising:
[0074] The teaching data collection module is used to obtain the test score data of each student in all subjects at different times during the pediatrics education and teaching process;
[0075] The teaching characteristic analysis module is used to obtain the periodic trend coefficient of each student in each time period according to the changes and differences in the test score data of each student in each subject in different time periods; determine the relative difference coefficient of each student based on the difference between the periodic trend coefficient of each student and other students in all time periods, and the long-term difference between the subject test score data of each student and other students in all time periods; construct the two-dimensional coordinates corresponding to each student through the relative difference coefficient of each student, combined with the test score data of each student in each subject at different times, so as to divide all students;
[0076] The targeted teaching adjustment module is used to carry out targeted education and teaching of pediatrics used for medical treatment according to the division results.
[0077] See also Figure 3 , Figure 3 The present invention is a block diagram of a pediatrics education and teaching device for medical use.
[0078] It is to be understood that the sequence of the embodiments of the present application described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0079] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.
[0080] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the protection scope of the present application.
Claims
1. A pediatrics education and teaching method for medical treatment, characterized in that: The method comprises the following steps: Obtain the test score data of each student in all subjects at different times during the pediatrics education and teaching process; The CRITIC algorithm is used to obtain the weight corresponding to the test score data of each subject of each student in the same time period. The weights of all subjects constitute the stage weight sequence of each student in the same time period. According to the distance between each student in each time period and the stage weight sequence of other time periods, and the change trend of all the distances of each student in each time period, the stage trend coefficient of each student in each time period is obtained; The process of obtaining the stage trend coefficient of each student in each time period is as follows: Analyze the distance between each student's stage weight sequence in each time period and other time periods, and record it as the stage weight difference of each student in each time period; The trend statistic of all the stage weight differences of each student in each time period is used as the stage trend coefficient of each student in each time period; The phase trend coefficients of all time periods of each student constitute the phase trend sequence of each student, and the distance between each student and the phase trend sequence of other students is analyzed as the phase difference of each student; The weight of each student's test score data of each subject at all times is recorded as the long-term weight, and the long-term weights of all subjects of each student constitute the long-term weight sequence of each student. The distance between the long-term weight sequence of each student and other students is recorded as the long-term difference of each student. Based on the difference between the periodic trend coefficients of each student and other students in all time periods and the difference between the long-term weight sequence of each student and other students, the relative difference coefficient of each student is determined; the relative difference coefficient of each student is the mean of the product of the periodic difference and the long-term difference between each student and all other students; through the relative difference coefficient of each student, combined with the test score data of each subject of each student at different times, the two-dimensional coordinates corresponding to each student are constructed, and all students are divided to obtain each personalized data set; The construction process of the two-dimensional coordinates corresponding to each student is: The sum of the test score data of all subjects of each student at each time is recorded as a vertical mapping value, the discrete degree of the vertical mapping value of each student at all times is used as the horizontal coordinate of each student, and the relative difference coefficient of each student is used as the vertical coordinate of each student to form a two-dimensional coordinate corresponding to each student; Each personalized data set is a set consisting of test score data of all students in each cluster obtained by clustering the two-dimensional coordinates of all students; Provide targeted education and teaching in pediatrics for medical treatment based on each personalized data set.
2. A pediatric internal medicine education and teaching method for medical treatment as claimed in claim 1, characterized in that: The targeted education and teaching of pediatrics for medical treatment based on each personalized data set further includes: The test score data of each subject in each personalized data set at different times are fitted to obtain the data change curve of each subject in each personalized data set, so as to configure corresponding teaching resources according to the performance of each category of students in different subjects.
3. A pediatric internal medicine education and teaching device for medical treatment, characterized in that: The pediatrics education and teaching device comprises: The teaching data collection module is used to obtain the test score data of each student in all subjects at different times during the pediatrics education and teaching process; The teaching characteristic analysis module uses the CRITIC algorithm to obtain the weight corresponding to the test score data of each subject of each student in the same time period. The weights of all subjects constitute the stage weight sequence of each student in the same time period. According to the distance between each student in each time period and the stage weight sequence of other time periods, and the change trend of all the distances of each student in each time period, the stage trend coefficient of each student in each time period is obtained; The process of obtaining the stage trend coefficient of each student in each time period is as follows: Analyze the distance between each student's stage weight sequence in each time period and other time periods, and record it as the stage weight difference of each student in each time period; The trend statistic of all the stage weight differences of each student in each time period is used as the stage trend coefficient of each student in each time period; The phase trend coefficients of all time periods of each student constitute the phase trend sequence of each student, and the distance between each student and the phase trend sequence of other students is analyzed as the phase difference of each student; The weight of each student's test score data of each subject at all times is recorded as the long-term weight, and the long-term weights of all subjects of each student constitute the long-term weight sequence of each student. The distance between the long-term weight sequence of each student and other students is recorded as the long-term difference of each student. Based on the difference between the periodic trend coefficients of each student and other students in all time periods and the difference between the long-term weight sequence of each student and other students, the relative difference coefficient of each student is determined; the relative difference coefficient of each student is the mean of the product of the periodic difference and the long-term difference between each student and all other students; through the relative difference coefficient of each student, combined with the test score data of each subject of each student at different times, the two-dimensional coordinates corresponding to each student are constructed, and all students are divided to obtain each personalized data set; The construction process of the two-dimensional coordinates corresponding to each student is: The sum of the test score data of all subjects of each student at each time is recorded as a vertical mapping value, the discrete degree of the vertical mapping value of each student at all times is used as the horizontal coordinate of each student, and the relative difference coefficient of each student is used as the vertical coordinate of each student to form a two-dimensional coordinate corresponding to each student; Each personalized data set is a set consisting of test score data of all students in each cluster obtained by clustering the two-dimensional coordinates of all students; The targeted teaching adjustment module is used to carry out targeted education and teaching of pediatrics used for medical treatment according to the division results.
Citation Information
Patent Citations
Learning process evaluation method and device, electronic equipment and medium
CN117670146A
Teaching system based on big data
CN118411275A
Intelligent education profiling analysis system
KR1020170140650A
