CN114493115A - Teaching quality analysis method and related equipment - Google Patents

Abstract

The embodiment of the invention provides a teaching quality analysis method, which comprises the steps of extracting target activity characteristics of target students in a first preset time period according to campus activity files of the target students; extracting historical activity characteristics and historical evaluation attributes corresponding to each student in a second preset time period from the historical campus activity files to obtain a historical activity characteristic set and a historical evaluation attribute set; predicting the evaluation attribute of the target student within third preset time according to the target activity feature, the historical activity feature set and the historical evaluation attribute set; and analyzing the teaching quality of the school in which the target student is located within a third preset time based on the evaluation attribute of the target student. The invention improves the prediction accuracy of the evaluation attribute, and can predict the evaluation attribute of students in any current or future time period, thereby accurately evaluating the current or future teaching quality and providing continuous and real-time reference for improving the teaching quality.

Description

Teaching quality analysis method and related equipment

technical field

The invention relates to the field of data processing, in particular to a teaching quality analysis method and related equipment.

Background technique

With the continuous development of education, the education of students has attracted more and more attention from parents and educators. How to improve the quality of teaching is a common concern in education work. The quality of teaching is also an important indicator to measure the teaching strength of schools. At present, the evaluation of teaching quality is mainly based on quantifiable assessment indicators, such as students' test scores, However, the test scores are limited by the assessment cycle, which is long and the assessment results are unstable. Moreover, the test scores are only an assessment index for the quality of history teaching, which leads to a lag in the improvement of teaching quality. Therefore, the existing teaching quality analysis The method cannot be assessed against the current teaching quality.

SUMMARY OF THE INVENTION

The embodiments of the present invention provide a teaching quality analysis method and related equipment, which improve the prediction accuracy of evaluation attributes, and can predict the evaluation attributes of students in any current or future time period, so that the current or future teaching quality can be accurately evaluated , providing continuous and real-time reference for teaching quality improvement.

In a first aspect, an embodiment of the present invention provides a teaching quality analysis method, the method comprising:

According to the campus activity file of the target student, extract the target activity feature of the target student within the first preset time period;

Extract the historical activity features and historical evaluation attributes corresponding to each student in the second preset time period from the historical campus activity archives, and obtain the historical activity feature set and historical evaluation attribute set;

According to the target activity feature, the historical activity feature set and the historical assessment attribute set, predict the assessment attribute of the target student within the third preset time;

The teaching quality of the school where the target student is located within a third preset time is analyzed based on the evaluation attribute of the target student.

Optionally, according to the target activity feature, the historical activity feature set and the historical assessment attribute set, predicting the assessment attribute of the target student within a third preset time, including:

Calculate the distance between the target activity feature and each of the historical activity features in the historical activity feature set, and determine the K historical activity features that are closest to the target activity feature distance;

Based on the K historical activity characteristics, determine K historical evaluation attributes corresponding to the K historical activity characteristics from the historical evaluation attribute set;

According to the K historical evaluation attributes, the evaluation attributes of the target student within the third preset time are determined.

Optionally, determining the evaluation attributes of the target student within a third preset time period according to the K historical evaluation attributes, including:

Calculate the frequency of occurrence of each type of historical evaluation attributes in the K historical evaluation attributes;

According to the historical evaluation attribute corresponding to the type with the highest occurrence frequency, the evaluation attribute of the target student within the third preset time is determined.

Optionally, before the step of calculating the distance between the target activity feature and the historical activity feature, and determining the K historical activity features closest to the target activity feature, the method further includes:

constructing a first data set, the first data set includes a first sample activity feature and a first evaluation attribute label corresponding to the first sample activity feature;

Divide the first data set into a training data set and a validation data set;

Initialize a K value, and perform training adjustment on the K value through the training data set to obtain the adjusted K value;

The adjusted K value is verified through the verification data set to determine the final K value.

Optionally, before the step of analyzing the teaching quality of the school where the target student is located within a third preset time based on the evaluation attribute of the target student, the method further includes:

Input the current target activity feature and the current evaluation attribute into a preset confidence network, and calculate the confidence of the current evaluation attribute;

If the confidence level satisfies a preset condition, adding the current target activity feature to the historical activity feature set, and adding the current evaluation attribute to the historical evaluation attribute set;

If the confidence level does not meet the preset condition, the current target activity feature is added to the secondary prediction queue according to the preset rule for waiting, and the secondary prediction queue is used to The target activity feature in the secondary prediction queue and the historical activity feature set are calculated again.

Optionally, the target activity feature and the historical activity feature are obtained by splicing each regional activity feature according to preset rules, and a campus area corresponding to a regional activity feature is described in the current target activity feature and the current evaluation attribute. Before inputting into a preset confidence network and calculating the confidence of the current evaluation attribute, the method further includes:

Build a confidence network and a second data set, the confidence network includes weight parameters and bias parameters corresponding to the regional activity features, the second data set includes the second sample activity features and the second sample activity The second evaluation attribute label corresponding to the sample activity feature;

The confidence network is trained through the second data set, and the confidence network is converged by continuously adjusting the weight parameter and the bias parameter, so as to obtain a trained confidence network, and the The trained confidence network is used as the preset confidence network.

Optionally, the teaching quality analysis based on the evaluation attributes of the target students includes:

Evaluate the campus environment according to the weight parameters in the trained confidence network, and obtain the evaluation result of the campus environment;

Teaching quality analysis is performed based on the evaluation result of the campus environment and the evaluation attributes of the target students.

In a second aspect, an embodiment of the present invention provides an apparatus for analyzing teaching quality, the apparatus comprising:

The first extraction module is used for extracting the target activity feature of the target student within the first preset time period according to the target student's campus activity file;

The second extraction module is used to extract the historical activity features and historical evaluation attributes corresponding to each student in the second preset time period from the historical campus activity archives, and obtain the historical activity feature set and the historical evaluation attribute set;

a prediction module, configured to predict the evaluation attributes of the target student within a third preset time according to the target activity feature, the historical activity feature set and the historical evaluation attribute set;

The analysis module is configured to analyze the teaching quality of the school where the target student is located within a third preset time based on the evaluation attribute of the target student.

In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, when the processor executes the computer program The steps in the teaching quality analysis method provided by the embodiment of the present invention are implemented.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, implements the teaching quality analysis method provided by the embodiment of the present invention. A step of.

In the embodiment of the present invention, according to the campus activity file of the target student, the target activity feature of the target student in the first preset time period is extracted; the historical activity feature corresponding to each student in the second preset time period is extracted from the historical campus activity file and the Historical evaluation attributes, obtain the historical activity feature set and historical evaluation attribute set; according to the target activity feature, historical activity feature set and historical evaluation attribute set, predict the evaluation attribute of the target student in the third preset time; based on the evaluation attribute of the target student Analyze the teaching quality of the target student's school within the third preset time. By filing students' campus activities, and extracting the target activity characteristics of students in the first preset time period from the students' campus activity files, and extracting the characteristics of each student's target activities in the second preset time period from the historical campus activity files Historical activity characteristics and historical evaluation attributes, using target activity characteristics, historical activity characteristics and historical evaluation attributes to predict students' evaluation attributes, and analyze teaching quality based on the predicted evaluation attributes, without waiting for a long evaluation cycle, using students' campus activities It can predict the evaluation attributes with the potential common connection between the evaluation attributes, which improves the prediction accuracy of the evaluation attributes, and can predict the evaluation attributes of students in the current or any future time period, so that the current or future teaching quality can be accurately evaluated. Provide continuous and real-time reference for teaching quality improvement.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a flowchart of a teaching quality analysis method provided by an embodiment of the present invention;

2 is a schematic structural diagram of a teaching quality analysis device provided by an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Please refer to FIG. 1. FIG. 1 is a flowchart of a teaching quality analysis method provided by an embodiment of the present invention. As shown in FIG. 1, the teaching quality analysis method includes the following steps:

101. According to the campus activity file of the target student, extract the target activity feature of the target student within the first preset time period.

In the embodiment of the present invention, the above-mentioned campus activity file refers to a data set recorded when students generate activities on campus, and the above-mentioned campus activity file can also be understood as a student-centered daily life file on campus.

Cameras with face recognition function can be installed in the preset campus areas, and each campus area can be captured and monitored through these cameras with face recognition function, so as to obtain the activity data of each student in each campus area, and put each student in each campus area. The activity data of each campus area and the corresponding evaluation attributes are archived as campus activity files. Further, if the assessment has not yet been carried out, it is only necessary to archive the activity data of each student in each campus area to the corresponding campus activity file. If the assessment has been carried out, the action data of each student in each campus area before the assessment is corresponding The assessment properties are archived as the Historic Campus Activities Archive.

The above campus areas refer to classrooms, corridors, stairs, libraries, gymnasiums, various campus sports venues (such as badminton courts, basketball courts, football fields, track and field fields, etc.), offices, canteens, canteens, and campus streets.

The above campus activity files can be divided into semesters, academic years or assessment cycles. For example, at the beginning of each semester, a campus activity file for the semester can be re-maintained for students, and updated in real time according to the captured activity data, corresponding to the previous semester. Archives of campus activities are maintained as historic campus archives. It is also possible to re-maintain a campus activity file for the school year at the beginning of each school year, and update it in real time according to the captured activity data, and maintain the campus activity file corresponding to the previous school year as a historical campus file. It is also possible to maintain a campus activity file of the current assessment cycle for students after the end of the previous assessment cycle, and update it in real time according to the captured activity data, and maintain the campus activity file corresponding to the previous assessment cycle as a historical campus file for maintenance.

The dimension of data collection in campus activity files includes activity data and basic file data. Among them, the activity data can be collected and identified according to the above-mentioned cameras with face recognition function, the above-mentioned basic file data can be collected and organized by registration materials, and the activity data can include people. Face capture attributes, face capture location, face capture time, etc. Basic file data can include student class data, learning data, class curriculum data, schedule data, and vacation time data.

The above-mentioned target students refer to students who need to perform evaluation attribute prediction. Specifically, the above-mentioned target students may be captured students. When a student is captured at a predetermined number of times in a campus area, the evaluation attribute can be predicted for the student, and the student is the target student. After receiving the prediction instruction from the user, the evaluation attribute prediction can be performed for all students. The above-mentioned evaluation attributes may be grades, characters, and the like.

The above-mentioned first preset time period may be a time period in units of weeks, months, assessment cycles, quarters, semesters, and school years. For example, the first preset time period may be the first quarter of the second grade of the current school year, and can The activity data of the target students in the first quarter of the second grade of the current school year are extracted from the students' campus activity files, and the target activity characteristics are extracted from the activity data. The above activity data can be shown in Table 1 below:

Table 1

Among them, Table 2 is the activity data and assessment attributes of the first quarter of the second grade of the current school year. In the activity data of Table 1, the number of times each student was captured in different campus areas is recorded, and the grades and personality are the corresponding assessment attributes. There is no assessment, so it is unknown.

The above target activity feature may be a feature in the form of a vector, for example, the target activity feature corresponding to Chen Dan may be (468, 220, 322, 10, 34, 16,...).

102. Extract the historical activity features and historical evaluation attributes corresponding to each student in the second preset time period from the historical campus activity file, and obtain a historical activity feature set and a historical evaluation attribute set.

In the embodiment of the present invention, the historical campus activity file includes historical activity data and historical evaluation attributes of each student.

The above-mentioned second preset time period can be determined according to the first preset time period and the predicted target. For example, if the first preset time period is the first quarter of grade 2, and the predicted target is the evaluation data of the target student in grade 3, then The second preset time period can be the first quarter of grade 3 in each historical academic year. At this time, the historical activity data and historical assessment attributes corresponding to each student in the first quarter of grade 3 can be extracted from the historical campus activity file, so that the historical activity Corresponding historical activity characteristics are extracted from the data, and corresponding historical activity characteristic sets and historical evaluation attribute sets are constructed according to the historical activity characteristics of each student. The above historical activity data and historical evaluation attributes can be shown in Table 2 below:

Table 2

Among them, Table 2 is the historical activity data and historical assessment attributes of the first quarter of grade 3 in each academic year. In the historical activity data of Table 2, the number of times each student was captured in different campus areas is recorded, and the grades and personality are corresponding The evaluation attribute is known because the evaluation has been carried out.

The above-mentioned target activity feature can be a feature in the form of a vector. For example, the target activity feature corresponding to Huang Dan can be (300, 120, 222, 50, 44, 6, ...), the historical evaluation attribute is grade A, and each character is different.

103. According to the target activity feature, the historical activity feature set, and the historical evaluation attribute set, predict the evaluation attribute of the target student within the third preset time.

In the embodiment of the present invention, the above-mentioned third preset time may be determined according to the prediction target, such as predicting the evaluation attributes of the target students in the next school year, if the first preset time is the first quarter of the current school year, then the third The preset time can be the assessment attribute of the first quarter of the next academic year.

Specifically, the similarity between the target activity characteristics and the historical activity characteristics can be used to predict the evaluation attributes of the target students, which is equivalent to the more similar the target students' activity data is to a certain historical activity data, the greater the probability that their evaluation attributes are the same. .

Optionally, the distance between each of the above-mentioned historical activity features in the above-mentioned target activity feature and the above-mentioned historical activity feature set can be calculated, and K historical activity features that are closest to the above-mentioned target activity feature distances are determined; based on the above-mentioned K historical activity features, K historical evaluation attributes corresponding to the above K historical activity features are determined from the above historical evaluation attribute set; according to the above K historical evaluation attributes, the evaluation attributes of the target student within the third preset time are determined.

The distance between the above-mentioned target activity feature and the historical activity feature can be the Euclidean distance, which can be calculated according to the following formula:

d=sqrt((x1-x2) ² +(y1-y2) ² +(z1-z2) ² +…)

Among them, d is the distance, (x1, y1, z1, ...) is the coordinates of the target activity feature in the Euclidean space, (x2, y2, z2, ...) is the coordinates of the historical activity feature in the Euclidean space.

The Euclidean distance between the target activity feature and all historical activity features in the historical activity feature set can be traversed to obtain the distance value between the target activity feature and each historical activity feature, and the K historical activity features with the smallest distance value are determined as the target activity feature. The closest K historical activity features.

Corresponding K historical evaluation attributes are determined from the above K historical activity characteristics, and the above historical activity characteristics and the historical evaluation attributes are associated by student names or student numbers. Specifically, after the K historical activity features are obtained, the corresponding K student information can be determined, and K historical evaluation attributes corresponding to the K student information can be determined in the historical evaluation attribute set according to the K student information.

The historical evaluation attribute with the highest number of occurrences of the K historical evaluation attributes can be selected as the evaluation attribute of the target student, so as to complete the prediction of the evaluation attribute of the target student.

Optionally, the occurrence frequency of each type of historical assessment attribute among the K historical assessment attributes may be calculated; the assessment attribute of the target student within the third preset time is determined according to the historical assessment attribute corresponding to the type with the highest occurrence frequency.

In the embodiment of the present invention, the above-mentioned historical evaluation attributes include an achievement dimension and a personality dimension. Specifically, the types of the achievement dimension may include types such as grade A, grade B, grade C, and grade D, and the type of personality dimension may include extroversion or introversion and other types. If among the K historical evaluation attributes, the historical evaluation attribute of grade A in the achievement dimension has the highest frequency, and the introverted historical evaluation attribute in the personality dimension has the highest frequency, then it can be determined that the evaluation attributes of the target student are grade A and introverted .

For example, taking K as 3, it can be shown in Table 3 below:

table 3

In Table 3, the historical activity characteristics of Huang Dan, Qu Hong, and Ye Ming are the closest to Chen Dan's target activity characteristics. If the frequency is 2 and the frequency of grade B is 1, then it can be determined that Chen Dan's evaluation attribute in the grade dimension is grade A; in the personality dimension, the frequency of extroversion among Huang Dan, Qu Hong, and Ye Ming is 2, and the frequency of introversion is 2. If it is 1, it can be determined that Chen Dan's evaluation attribute in the personality dimension is outgoing.

Optionally, a first data set can be constructed, and the first data set includes a first sample activity feature and a first evaluation attribute label corresponding to the first sample activity feature; the first data set is divided into a training data set and a verification data set. Data set; initialize a K value, and adjust the K value through the training data set to obtain the adjusted K value; verify the adjusted K value through the verification data set to determine the final K value. The first sample activity feature may be a historical activity feature.

Specifically, a small K value, such as 1, can be initialized, and the K value is increased during the training adjustment process of the K value through the training data set. The final K value can be determined by the variance of the validation data set, and the K value corresponding to the lowest variance of the validation data set can be taken as the final K value.

The variance of the validation dataset is determined according to the degree of difference between the error of the training dataset and the error of the validation dataset. The greater the difference between the error of the training dataset and the error of the validation dataset, the higher the variance of the validation dataset. The error is 1%, the error on the validation set is 11%, and the error on the training data set is quite different from the error on the validation set, which means that the validation data set has high variance. By determining an appropriate K value, the prediction accuracy of the evaluation attributes can be improved.

104. Analyze the teaching quality of the school where the target student is located within the third preset time period based on the evaluation attribute of the target student.

In the embodiment of the present invention, by predicting the evaluation attributes of the target students, the evaluation attributes of all the target students can be predicted before the evaluation, so that the teaching quality of the school where the target students are located can be analyzed according to the predicted evaluation attributes. , the teaching quality of the school where the target student is located within the third preset time can be analyzed according to the predicted evaluation attributes, so as to obtain the teaching quality of the school where the target student is located within the third preset time.

Optionally, before step 104, the current target activity feature and the current evaluation attribute can also be input into a preset confidence network to calculate the confidence of the current evaluation attribute; if the confidence meets the preset conditions, the current target The activity feature is added to the historical activity feature set, and the current evaluation attribute is added to the historical evaluation attribute set; if the confidence level does not meet the preset conditions, the current target activity feature is added to the secondary prediction queue according to the preset rules for waiting, among which , the secondary prediction queue is used to calculate the target activity feature and historical activity feature set in the secondary prediction queue again after all target activity feature processing is completed.

A confidence prediction can be made on the predicted target activity characteristics and the predicted evaluation attributes through a preset confidence network. The above confidence is the credibility of the predicted evaluation attributes. The higher the confidence, the predicted evaluation attributes. The more credible the attribute and the lower the confidence, the less credible the predicted evaluation attribute is.

When the confidence of the current evaluation attribute satisfies the preset condition, the current evaluation attribute can be considered credible, and when the confidence degree of the current evaluation attribute does not meet the preset condition, the current evaluation attribute can be considered unreliable. When the current evaluation attribute is credible, the corresponding current target activity feature can be temporarily added to the historical activity feature set, and the current evaluation attribute can be temporarily added to the historical evaluation attribute set. In this way, the historical activity feature set and historical evaluation can be expanded. The attribute set is used to calculate the target activity features in the secondary prediction queue with more historical activity features. In the case where the current evaluation attribute is unreliable, the current target activity feature is added to the secondary prediction queue according to the preset rules for waiting. After the processing is completed, it will be started, and the target activity feature and historical activity feature set in the queue will be calculated again.

Optionally, in this embodiment of the present invention, the target activity feature and the historical activity feature can be obtained by splicing each regional activity feature according to preset rules, and a campus area corresponding to one regional activity feature can construct a confidence network and a second data. The confidence network includes weight parameters and bias parameters corresponding to the regional activity characteristics, and the second data set includes the second sample activity characteristics and the second evaluation attribute labels corresponding to the second sample activity characteristics; through the second data set The confidence network is trained, and the confidence network is converged by continuously adjusting the weight parameters and bias parameters to obtain a trained confidence network; the trained confidence network is used as the preset confidence network. The second sample activity feature may be a historical activity feature.

Further, a confidence network can be constructed based on a linear logistic regression model. The constructed confidence network includes multiple weight parameters and multiple bias parameters. One weight parameter corresponds to one regional activity feature, and the above target activity feature can be passed through (x1 , x2, x3,...), the above historical activity features can be represented by (x1', x2', x3',...), where the target activity features are the regional activity features x1, x2, x3,... spliced to get , for example, x1 represents the regional activity feature of the classroom, x2 represents the regional activity feature of the corridor, x3 represents the regional activity feature of the stairs, and the weight parameters can be set to w1, w2, w3, ... where w1 can correspond to x1, and w2 can correspond to For x2, w3 may correspond to x3. Specifically, the algorithm of the confidence network can be shown as the following formula:

f(x)=w ^T x+b

Among them, f(x) is the calculation result of the confidence network, w is the weight parameter, b is the bias parameter, and training is performed with f(xi)≈yi as the target, where y is the label value, which can be manually labeled Label. In the training process, it can be carried out by minimizing the mean square error, as shown in the following formula:

Among them, m is the total number of samples, the larger the mean square error, the worse the confidence network effect, the smaller the mean square error, the better the confidence network effect, the training process is to minimize the mean square error as the target pair The weight parameters and bias parameters in the confidence network are iteratively adjusted.

During the adjustment process of the above weight parameters, the following formula can be used:

During the adjustment process of the above bias parameters, the following formula can be used:

In the embodiment of the present invention, the evaluation attributes and confidence of the target student can be predicted and obtained. For example, the performance of Chen Dan 2 in the first quarter of the next academic year is: grade A, outgoing personality, and confidence of 60%.

Optionally, in the embodiment of the present invention, the campus environment can be evaluated according to the weight parameters in the trained confidence network to obtain the campus environment evaluation result; the teaching quality analysis is carried out based on the campus environment evaluation result and the evaluation attributes of the target students. .

Specifically, the weight w parameter in the trained confidence network can reflect the influence of each campus area on the student evaluation attributes. Therefore, the campus environment can be evaluated according to the weight parameters in the trained confidence network. Specifically, a campus area with a large weight parameter can be considered to have a positive impact on students, and the teaching quality is good; for a campus area with a small weight parameter, it can be considered that there is no or negative impact on students, and the teaching quality is average or Not good, so we can analyze the teaching quality according to the evaluation results of the campus environment.

In a possible embodiment, the area or number of areas may be appropriately increased for a campus area with a larger weight parameter, and the area or number of areas may be appropriately decreased for a campus area with a smaller weight parameter, thereby improving teaching quality.

In the embodiment of the present invention, according to the campus activity file of the target student, the target activity feature of the target student in the first preset time period is extracted; the historical activity feature corresponding to each student in the second preset time period is extracted from the historical campus activity file and the Historical evaluation attributes, obtain the historical activity feature set and historical evaluation attribute set; according to the target activity feature, historical activity feature set and historical evaluation attribute set, predict the evaluation attribute of the target student in the third preset time; based on the evaluation attribute of the target student Conduct teaching quality analysis. By filing students' campus activities, and extracting the target activity characteristics of students in the first preset time period from the students' campus activity files, and extracting the characteristics of each student's target activities in the second preset time period from the historical campus activity files Historical activity characteristics and historical evaluation attributes, using target activity characteristics, historical activity characteristics and historical evaluation attributes to predict students' evaluation attributes, and analyze teaching quality based on the predicted evaluation attributes, without waiting for a long evaluation cycle, using students' campus activities It can predict the evaluation attributes with the potential common connection between the evaluation attributes, which improves the prediction accuracy of the evaluation attributes, and can predict the evaluation attributes of students in the current or any future time period, so that the current or future teaching quality can be accurately evaluated. Provide continuous and real-time reference for teaching quality improvement.

It should be noted that the teaching quality analysis method provided by the embodiment of the present invention can be applied to devices such as smart phones, computers, and servers that can perform teaching quality analysis.

Optionally, please refer to FIG. 2. FIG. 2 is a schematic structural diagram of a teaching quality analysis device provided by an embodiment of the present invention. As shown in FIG. 2, the device includes:

The first extraction module 201 is used for extracting the target activity feature of the target student within the first preset time period according to the target student's campus activity file;

The second extraction module 202 is configured to extract the historical activity feature and historical evaluation attribute corresponding to each student in the second preset time period from the historical campus activity file, and obtain the historical activity feature set and the historical evaluation attribute set;

A prediction module 203, configured to predict the evaluation attributes of the target student within a third preset time period according to the target activity feature, the historical activity feature set and the historical evaluation attribute set;

The analysis module 204 is configured to analyze the teaching quality of the school where the target student is located within a third preset time based on the evaluation attribute of the target student.

Optionally, the prediction module 203 includes:

A calculation submodule for calculating the distance between the target activity feature and each of the historical activity features in the historical activity feature set, and determining the K historical activity features that are closest to the target activity feature distance;

a first determining submodule, configured to determine K historical evaluation attributes corresponding to the K historical activity characteristics from the historical evaluation attribute set based on the K historical activity characteristics;

The second determination sub-module is configured to determine the evaluation attributes of the target student within the third preset time according to the K historical evaluation attributes.

Optionally, the second determination submodule includes:

a calculation unit, used to calculate the frequency of occurrence of each type of historical evaluation attributes in the K historical evaluation attributes;

A determining unit, configured to determine the evaluation attribute of the target student within the third preset time period according to the historical evaluation attribute corresponding to the type with the highest occurrence frequency.

Optionally, the prediction module 203 further includes:

a construction submodule for constructing a first data set, where the first data set includes a first sample activity feature and a first evaluation attribute label corresponding to the first sample activity feature;

A division sub-module for dividing the first data set into a training data set and a verification data set;

A training submodule, used for initializing a K value, and performing training adjustment on the K value through the training data set to obtain an adjusted K value;

The third determination sub-module is configured to perform verification processing on the adjusted K value by using the verification data set to determine the final K value.

Optionally, the device further includes:

The calculation module is used to input the current target activity feature and the current evaluation attribute into the preset confidence network, calculate the confidence of the current evaluation attribute, and the secondary prediction queue is used to complete the processing of all the target activity characteristics Then calculate the target activity feature and the historical activity feature set in the secondary prediction queue again;

a first adding module, configured to add the current target activity feature to the historical activity feature set if the confidence level satisfies a preset condition, and add the current evaluation attribute to the historical evaluation attribute set;

The second adding module is configured to add the current target activity feature to the secondary prediction queue for waiting according to a preset rule if the confidence level does not meet the preset condition.

Optionally, the target activity feature and the historical activity feature are obtained by splicing each regional activity feature according to preset rules, and a campus area corresponding to one regional activity feature, the device further includes:

a building module for constructing a confidence network and a second data set, the confidence network includes weight parameters and bias parameters corresponding to the regional activity feature, the second data set includes the second sample activity feature and a second evaluation attribute label corresponding to the second sample activity feature;

A training module, configured to train the confidence network through the second data set, and make the confidence network converge by continuously adjusting the weight parameter and the bias parameter to obtain a trained confidence network, and use the trained confidence network as the preset confidence network.

Optionally, the analysis module 204 includes:

An evaluation sub-module, used to evaluate the campus environment according to the weight parameters in the trained confidence network, and obtain the evaluation result of the campus environment;

The analysis sub-module is used to analyze the teaching quality based on the evaluation result of the campus environment and the evaluation attributes of the target students.

It should be noted that the teaching quality analysis apparatus provided in the embodiment of the present invention may be applied to devices such as smart phones, computers, and servers that can perform teaching quality analysis.

The teaching quality analysis device provided by the embodiment of the present invention can realize the various processes implemented by the teaching quality analysis method in the above method embodiments, and can achieve the same beneficial effect. In order to avoid repetition, details are not repeated here.

Referring to FIG. 3, FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As shown in FIG. 3, it includes: a memory 302, a processor 301, and a memory 302 and a processor 301 stored in the memory 302 and available on the processor 301 A computer program for teaching quality analysis methods that run on:

The processor 301 is used for calling the computer program stored in the memory 302, and performs the following steps:

According to the campus activity file of the target student, extract the target activity feature of the target student within the first preset time period;

Extract the historical activity features and historical evaluation attributes corresponding to each student in the second preset time period from the historical campus activity archives, and obtain the historical activity feature set and historical evaluation attribute set;

According to the target activity feature, the historical activity feature set and the historical assessment attribute set, predict the assessment attribute of the target student within the third preset time;

The teaching quality of the school where the target student is located within a third preset time is analyzed based on the evaluation attribute of the target student.

Optionally, the predicting the evaluation attribute of the target student within the third preset time according to the target activity feature, the historical activity feature set and the historical evaluation attribute set executed by the processor 301 includes:

Calculate the distance between the target activity feature and each of the historical activity features in the historical activity feature set, and determine the K historical activity features that are closest to the target activity feature distance;

Based on the K historical activity characteristics, determine K historical evaluation attributes corresponding to the K historical activity characteristics from the historical evaluation attribute set;

According to the K historical evaluation attributes, the evaluation attributes of the target student within the third preset time are determined.

Optionally, determining the evaluation attributes of the target student within the third preset time period according to the K historical evaluation attributes performed by the processor 301 includes:

Calculate the frequency of occurrence of each type of historical evaluation attributes in the K historical evaluation attributes;

According to the historical evaluation attribute corresponding to the type with the highest occurrence frequency, the evaluation attribute of the target student within the third preset time is determined.

Optionally, before the step of calculating the distance between the target activity feature and the historical activity feature, and determining the K historical activity features closest to the target activity feature, all the steps performed by the processor 301 are performed. The method also includes:

constructing a first data set, the first data set includes a first sample activity feature and a first evaluation attribute label corresponding to the first sample activity feature;

Divide the first data set into a training data set and a validation data set;

Initialize a K value, and perform training adjustment on the K value through the training data set to obtain the adjusted K value;

The adjusted K value is verified through the verification data set to determine the final K value.

Optionally, before the step of performing teaching quality analysis based on the evaluation attributes of the target students, the method executed by the processor 301 further includes:

Input the current target activity feature and the current evaluation attribute into a preset confidence network, and calculate the confidence of the current evaluation attribute;

If the confidence level satisfies a preset condition, adding the current target activity feature to the historical activity feature set, and adding the current evaluation attribute to the historical evaluation attribute set;

If the confidence level does not meet the preset condition, the current target activity feature is added to the secondary prediction queue according to the preset rule for waiting, and the secondary prediction queue is used to The target activity feature in the secondary prediction queue and the historical activity feature set are calculated again

Optionally, the target activity feature and the historical activity feature are obtained by splicing each regional activity feature according to preset rules, and a campus area corresponding to a regional activity feature is described in the current target activity feature and the current evaluation attribute. The method performed by the processor 301 further includes:

Build a confidence network and a second data set, the confidence network includes weight parameters and bias parameters corresponding to the regional activity features, the second data set includes the second sample activity features and the second sample activity The second evaluation attribute label corresponding to the sample activity feature;

The confidence network is trained through the second data set, and the confidence network is converged by continuously adjusting the weight parameter and the bias parameter, so as to obtain a trained confidence network, and the The trained confidence network is used as the preset confidence network.

Optionally, the teaching quality analysis based on the evaluation attribute of the target student performed by the processor 301 includes:

Evaluate the campus environment according to the weight parameters in the trained confidence network, and obtain the evaluation result of the campus environment;

Teaching quality analysis is performed based on the evaluation result of the campus environment and the evaluation attributes of the target students.

The electronic device provided by the embodiment of the present invention can implement each process implemented by the teaching quality analysis method in the above method embodiment, and can achieve the same beneficial effect. In order to avoid repetition, details are not repeated here.

Embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the teaching quality analysis method or application-side teaching quality analysis provided by the embodiment of the present invention is implemented. Each process of the method can achieve the same technical effect. To avoid repetition, details are not repeated here.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. During execution, the processes of the embodiments of the above-mentioned methods may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM for short).

The above disclosures are only preferred embodiments of the present invention, and of course, the scope of the rights of the present invention cannot be limited by this. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims (10)

1. a teaching quality analysis method, is characterized in that, comprises the following steps: According to the campus activity file of the target student, extract the target activity feature of the target student within the first preset time period; Extract the historical activity features and historical evaluation attributes corresponding to each student in the second preset time period from the historical campus activity archives, and obtain the historical activity feature set and historical evaluation attribute set; According to the target activity feature, the historical activity feature set and the historical assessment attribute set, predict the assessment attribute of the target student within the third preset time; The teaching quality of the school where the target student is located within a third preset time is analyzed based on the evaluation attribute of the target student. 2. The method according to claim 1, wherein, according to the target activity feature, the historical activity feature set and the historical evaluation attribute set, predicting that the target student will be within a third preset time assessment attributes, including: Calculate the distance between the target activity feature and each of the historical activity features in the historical activity feature set, and determine the K historical activity features that are closest to the target activity feature distance; Based on the K historical activity characteristics, determine K historical evaluation attributes corresponding to the K historical activity characteristics from the historical evaluation attribute set; According to the K historical evaluation attributes, the evaluation attributes of the target student within the third preset time are determined. 3. The method according to claim 2, wherein, determining the evaluation attributes of the target student within a third preset time according to the K historical evaluation attributes, comprising: Calculate the frequency of occurrence of each type of historical evaluation attributes in the K historical evaluation attributes; According to the historical evaluation attribute corresponding to the type with the highest occurrence frequency, the evaluation attribute of the target student within the third preset time is determined. 4. The method according to claim 2, wherein, in the calculating the distance between the target activity feature and the historical activity feature, and determining the K historical activities that are closest to the target activity feature Before the step of characterizing, the method further includes: constructing a first data set, the first data set includes a first sample activity feature and a first evaluation attribute label corresponding to the first sample activity feature; Divide the first data set into a training data set and a validation data set; Initialize a K value, and perform training adjustment on the K value through the training data set to obtain the adjusted K value; The adjusted K value is verified through the verification data set to determine the final K value. 5. The method according to claim 1, wherein, before the step of analyzing the teaching quality of the school where the target student is located within a third preset time based on the evaluation attribute of the target student, The method also includes: Input the current target activity feature and the current evaluation attribute into a preset confidence network, and calculate the confidence of the current evaluation attribute; If the confidence level satisfies a preset condition, adding the current target activity feature to the historical activity feature set, and adding the current evaluation attribute to the historical evaluation attribute set; If the confidence level does not meet the preset condition, the current target activity feature is added to the secondary prediction queue according to the preset rule for waiting, and the secondary prediction queue is used to The target activity feature in the secondary prediction queue and the historical activity feature set are calculated again. 6. The method of claim 5, wherein the target activity feature and the historical activity feature are obtained by splicing each regional activity feature according to preset rules, and a campus area corresponding to a regional activity feature is Before the step of inputting the current target activity feature and the current evaluation attribute into a preset confidence network and calculating the confidence of the current evaluation attribute, the method further includes: Build a confidence network and a second data set, the confidence network includes weight parameters and bias parameters corresponding to the regional activity features, the second data set includes the second sample activity features and the second sample activity The second evaluation attribute label corresponding to the sample activity feature; The confidence network is trained through the second data set, and the confidence network is converged by continuously adjusting the weight parameter and the bias parameter, so as to obtain a trained confidence network, and the The trained confidence network is used as the preset confidence network. 7. The method according to claim 6, wherein the analyzing the teaching quality based on the evaluation attributes of the target students comprises: Evaluate the campus environment according to the weight parameters in the trained confidence network, and obtain the evaluation result of the campus environment; Teaching quality analysis is performed based on the evaluation result of the campus environment and the evaluation attributes of the target students. 8. A teaching quality analysis device, wherein the device comprises: The first extraction module is used for extracting the target activity feature of the target student within the first preset time period according to the target student's campus activity file; The second extraction module is used to extract the historical activity characteristics and historical evaluation attributes corresponding to each student in the second preset time period from the historical campus activity archives, and obtain the historical activity characteristic set and the historical evaluation attribute set; a prediction module, configured to predict the evaluation attributes of the target student within a third preset time according to the target activity feature, the historical activity feature set and the historical evaluation attribute set; The analysis module is configured to analyze the teaching quality of the school where the target student is located within a third preset time based on the evaluation attribute of the target student. 9. An electronic device, characterized in that it comprises: a memory, a processor and a computer program stored on the memory and running on the processor, the processor implementing the computer program as claimed when executing the computer program Steps in the teaching quality analysis method described in any one of requirements 1 to 7. 10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program according to any one of claims 1 to 7 is implemented. Steps in a Teaching Quality Analysis Method.

Images