Teaching basic skill capability evaluation report generation method for medical teachers

Abstract

The invention relates to the field of data evaluation, in particular to a teaching basic skill capability evaluation report generation method for medical teachers, which comprises the following steps of: shooting and scanning basic images of teaching basic skill capability evaluation corresponding to each medical teacher, and obtaining evaluation entries of teaching basic skill corresponding to each medical teacher according to the basic images; the method comprises the following steps: generating a plurality of standard index characteristics in evaluation entries, filling the standard index characteristics into an evaluation report as an evaluation catalogue, extracting keywords in the evaluation entries by an extractor according to the standard index characteristics, classifying the keywords by an automatic filling device, enabling the keywords to correspond to the evaluation catalogue, automatically filling the keywords into the evaluation report, and analyzing a text. The efficiency and accuracy of evaluation report generation are improved, the complexity of manual operation is reduced through an automatic mode, meanwhile, the objectivity and consistency of evaluation are ensured, and more accurate analysis and evaluation are provided for teaching quality.

Description

Technical Field

[0001] The present invention relates to the field of data evaluation, and in particular to a method for generating a basic teaching function evaluation report for medical teachers. Background Art

[0002] Competence evaluation involves multiple areas, including six basic functional abilities: lesson plan writing ability, classroom design ability, teaching reflection ability, teaching tool use ability, bedside teaching ability, question setting and exam supervision ability. In teaching evaluation, competence evaluation technology can help extract key information from student evaluation texts, such as teachers' teaching attitude, teaching content, teaching ability, teaching methods and teaching effects. Through competence evaluation technology, valuable information can be effectively extracted from a large amount of data, a comprehensive evaluation system can be constructed, and detailed and accurate evaluation reports can be generated.

[0003] Chinese patent application publication number: CN104616548A discloses a teaching effect evaluation system for education and training, including: an auditory attention test module, used to test the improvement of auditory attention of each student before and after training and calculate the first teaching score; an auditory memory test module, used to test the improvement of auditory memory of each student before and after training and calculate the second teaching score; a visual resolution test module, used to test the improvement of visual resolution of each student before and after training and calculate the third teaching score; a visual-motor integration ability test module, used to test the improvement of visual-motor integration ability of each student before and after training and calculate the fourth teaching score; a test evaluation module, used to generate a test report for each student according to the test results of each item, and calculate the teaching evaluation score of the teacher in charge of the class according to the scores of each item, so as to evaluate the teaching effect of the teacher in charge of the class according to the level of the teaching evaluation score. The system is conducive to comprehensive assessment and evaluation of teaching effects.

[0004] Chinese patent application publication number: CN118365198A discloses a method for processing student evaluation data, including: pre-defining project parameters that characterize the school's actual ability to cultivate students, defining a school business model based on the project parameters; creating training indicators based on the school business model; collecting school-based course data, and constructing a mapping relationship between the school-based course data and the training indicators; setting evaluation parameters based on the training indicators; generating student evaluation results based on the evaluation parameters and the school-based course data; wherein the project parameters include: teaching goal characteristic values, course setting characteristic values, and evaluation method characteristic values. By pre-defining project parameters, creating training indicators, constructing mapping relationships, and setting evaluation parameters, accurate processing and intelligent generation of student evaluation data are achieved under the premise of complying with the school business model. The system and electronic equipment also provided by the invention have corresponding advantages.

[0005] However, the above method has the following problem: it is not possible to automatically classify the data and thus automatically generate an evaluation report. Summary of the invention

[0006] To this end, the present invention provides a method for generating a basic teaching function evaluation report for medical teachers, so as to overcome the problem in the prior art that data cannot be automatically classified to automatically generate an evaluation report.

[0007] To achieve the above object, the present invention provides a method for generating a basic teaching function evaluation report for medical teachers, comprising:

[0008] Photograph and scan the basic images for evaluating the basic teaching skills of each medical teacher, and obtain the evaluation terms for the basic teaching skills of each medical teacher based on the basic images;

[0009] Generate several standard indicator features in the evaluation terms and fill them into the evaluation report as the evaluation catalog, where:

[0010] When a new evaluation term appears, the corresponding indicator feature is generated;

[0011] The standard indicator features include the evaluation type and evaluation result of the evaluation item, and,

[0012] Use semantic recognition to merge several indicator features and generate corresponding standard indicator features;

[0013] The extractor extracts the keywords in the evaluation terms according to the standard indicator characteristics, wherein:

[0014] The extractor is provided with a keyword extraction model;

[0015] The automatic filler classifies the keywords, corresponds to the evaluation catalog, and automatically fills them into the evaluation report;

[0016] The evaluation report generated by the automatic filler is related to the corresponding basic image.

[0017] Furthermore, the step of obtaining the evaluation terms includes:

[0018] The corresponding basic teaching function evaluation of each medical teacher is photographed to form the corresponding basic image;

[0019] Performing text scanning on the basic image to obtain text scanning information corresponding to the teaching basic functional ability evaluation;

[0020] The word segmenter screens the text scanning information to obtain corresponding evaluation terms, wherein:

[0021] The word segmenter is provided with a word segmentation model for tracking and screening the evaluation words.

[0022] Furthermore, the step of filtering the text scanning information by the word segmenter includes:

[0023] The term extraction model segments the text scanning information according to semantics to form a number of text words;

[0024] Sorting the text words according to the number of words in the text to form a preliminary text;

[0025] Preprocessing the primary selected text to form corresponding text preprocessing data;

[0026] The term extraction model receives the text preprocessing data and performs learning to generate corresponding evaluation terms.

[0027] Furthermore, the step of preprocessing the primary selected text includes:

[0028] The primary selected text is cleaned to form corresponding text cleaning data, wherein:

[0029] The text cleaning is to remove text words in the primary selected text that are below a matching threshold;

[0030] The matching threshold is the minimum standard for the matching degree between the text vocabulary and the evaluation type and / or the evaluation result;

[0031] The text cleaning data is standardized to form corresponding text preprocessing data, wherein:

[0032] The standardization process is to cut the text cleaning data according to a standard sampling rate;

[0033] The standard sampling rate is a sampling rate that can be recognized by the term extraction model, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0034] Furthermore, the steps of training the term extraction model include:

[0035] The term extraction model is iteratively optimized according to the text preprocessing data set until the loss value converges to a preset value, wherein:

[0036] The text preprocessing data set includes text preprocessing data formed by standardizing each text cleaning data;

[0037] Testing the current term extraction model using the text preprocessing data set;

[0038] When the test result meets the preset test result, the parameters of the term extraction model are saved.

[0039] Furthermore, the steps of filling the evaluation catalogue into the evaluation report include:

[0040] Extracting keywords of the evaluation terms and dividing the standard indicator features;

[0041] Classifying the evaluation terms according to the standard indicator characteristics to form a corresponding evaluation catalog;

[0042] Fill the evaluation catalogue into the evaluation report.

[0043] Furthermore, the step of extracting keywords from the evaluation entries includes:

[0044] The keyword extraction model receives and stores the standard indicator features;

[0045] Counting the occurrence frequency of the keywords, and determining the extraction priority of the keywords according to the occurrence frequency,

[0046] Wherein, a frequency threshold is set in the keyword extraction model;

[0047] The keyword extraction model extracts keywords from the evaluation terms according to the extraction priority.

[0048] Further, when the occurrence frequency of the keyword is greater than the frequency threshold, the priority of the keyword is determined as priority extraction, and when the occurrence frequency of the keyword is less than the frequency threshold, the priority of the keyword is determined as normal extraction.

[0049] Furthermore, the automatic filler classifies the keywords according to the classification standard, wherein:

[0050] The classification criteria include the semantics, part of speech and / or context relevance of the keyword.

[0051] Furthermore, the classified keywords are matched with corresponding parts in the evaluation catalog, and according to the matching results, the keywords are automatically filled into corresponding parts of the evaluation report.

[0052] Compared with the prior art, the present invention photographs and scans basic images for evaluating the basic teaching skills of each medical teacher, obtains evaluation entries for the basic teaching skills of each medical teacher based on the basic images, generates several standard indicator features in the evaluation entries, and fills them into the evaluation report as an evaluation catalog. The extractor extracts the keywords in the evaluation entries based on the standard indicator features, and the automatic filler classifies the keywords, corresponds to the evaluation catalog, and automatically fills them into the evaluation report. By analyzing the text, the efficiency and accuracy of the evaluation report generation are improved. Through automation, the tediousness of manual operation is reduced, while ensuring the objectivity and consistency of the evaluation, providing more accurate analysis and evaluation for the teaching quality.

[0053] Furthermore, by photographing and scanning the basic images of the basic teaching function evaluation corresponding to each medical teacher, the corresponding evaluation terms are obtained, and text information is effectively extracted from the basic images to provide data support for the subsequent evaluation report generation, which not only improves the efficiency of the evaluation, but also enhances the objectivity and accuracy of the evaluation.

[0054] Furthermore, by segmenting and sorting the text scanning information according to semantics, preprocessing the preliminary text, and using the term segmentation model to learn the text preprocessing data, the corresponding evaluation terms are generated, and the terms for teaching evaluation are extracted, processed, and generated from the original text scanning information. This process not only involves text mining and natural language processing technologies, but also includes the application of machine learning, which improves the accuracy and efficiency of evaluation. Through the application of these technologies, valuable information can be effectively extracted from a large amount of text data, providing a scientific and objective basis for teaching evaluation.

[0055] Furthermore, by cleaning and standardizing the preliminary texts, corresponding text preprocessing data is formed, which prepares data for natural language processing and text mining, ensures the quality of the data and the accuracy of the model, and effectively extracts valuable information from large amounts of text data, providing a scientific and objective basis for teaching evaluation.

[0056] Furthermore, by training the term extraction model, the term extraction model can be effectively trained and optimized to achieve reliable performance, thereby ensuring its accuracy and reliability in practical applications.

[0057] Furthermore, by extracting the keywords of the evaluation terms, dividing the standard indicator characteristics, and classifying the evaluation terms according to the standard indicator characteristics, a corresponding evaluation catalog is formed and filled into the evaluation report, thereby ensuring the accuracy, completeness and usefulness of the evaluation report, and providing a detailed evaluation of the basic teaching functions of medical teachers, which not only improves the efficiency of the evaluation, but also enhances the objectivity and systematicness of the evaluation.

[0058] Furthermore, by extracting keywords from evaluation entries and comparing the frequency of occurrence of keywords with the frequency threshold, the keyword extraction model can effectively extract keywords from evaluation entries based on the frequency of occurrence of keywords and the preset frequency threshold, which facilitates the generation of evaluation reports and the analysis of teaching evaluations.

[0059] Furthermore, by matching the classified keywords with the corresponding parts in the evaluation catalog, the keywords are automatically filled into the corresponding parts of the evaluation report, so that the automatic filler can effectively classify the keywords and fill them into the evaluation report, thereby improving the efficiency and accuracy of evaluation report generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of the method for generating a teaching basic function evaluation report for medical teachers of the present invention;

[0061] Figure 2 A flow chart for obtaining evaluation terms for the present invention;

[0062] Figure 3 A flow chart of the word segmenter of the present invention screening text scanning information;

[0063] Figure 4 The present invention is a flowchart for training the term extraction model. DETAILED DESCRIPTION

[0064] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0066] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0067] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0068] See also Figure 1 As shown, it is a flow chart of the method for generating a teaching basic function evaluation report for medical teachers of the present invention, comprising:

[0069] Step S1, photographing and scanning the basic image of the evaluation of the basic teaching skills of each medical teacher, and obtaining the evaluation terms of the basic teaching skills of each medical teacher according to the basic image;

[0070] Step S2, generating several standard indicator features in the evaluation entry, and filling them into the evaluation report as the evaluation catalog, wherein:

[0071] When a new evaluation term appears, the corresponding indicator feature is generated;

[0072] Standard indicator features include the evaluation type and evaluation result of the evaluation term, as well as,

[0073] Use semantic recognition to merge several indicator features and generate corresponding standard indicator features;

[0074] Step S3, the extractor extracts the keywords in the evaluation entry according to the standard indicator characteristics, wherein:

[0075] The extractor is provided with a keyword extraction model;

[0076] Step S4, the automatic filler classifies the keywords, corresponds to the evaluation catalog, and automatically fills them into the evaluation report;

[0077] Among them, the evaluation report generated by the automatic filler is related to the corresponding basic image.

[0078] In the specific implementation, the evaluation types include: lesson plan writing ability, classroom design ability, teaching reflection ability, teaching tool use ability, bedside teaching ability, question setting and examination supervision ability.

[0079] By photographing and scanning the basic images for evaluating the basic teaching skills of each medical teacher, and obtaining the evaluation terms for the basic teaching skills of each medical teacher based on the basic images, a number of standard indicator features in the evaluation terms are generated and filled into the evaluation report as an evaluation catalog. The extractor extracts the keywords in the evaluation terms according to the standard indicator features, and the automatic filler classifies the keywords, corresponds to the evaluation catalog, and automatically fills them into the evaluation report. By analyzing the text, the efficiency and accuracy of the evaluation report generation are improved. Through automation, the tediousness of manual operations is reduced, while ensuring the objectivity and consistency of the evaluation, providing a more accurate analysis and evaluation of the teaching quality.

[0080] See also Figure 2 As shown, it is a flow chart of obtaining evaluation terms in the present invention, including:

[0081] Step S11, photographing the corresponding teaching basic functional ability evaluation of each medical teacher to form a corresponding basic image;

[0082] Step S12, performing text scanning on the basic image to obtain text scanning information corresponding to the evaluation of the basic teaching function;

[0083] Step S13, the word segmenter screens the text scanning information to obtain the corresponding evaluation terms, wherein:

[0084] The word segmenter is provided with a word segmentation model for tracking and screening evaluation words.

[0085] In the specific implementation, the basic image is captured by scanning paper documents or directly photographing teaching materials such as blackboards and whiteboards. After obtaining the basic images, these images are scanned for text, and optical character recognition technology is usually used to convert the text in the image into an editable text format. The word segmenter uses a term segmentation model to filter and extract keywords or evaluation terms in the text. This model is based on a machine learning algorithm that can identify and track specific evaluation terms, thereby extracting data useful for generating evaluation reports.

[0086] The advantages of this process are:

[0087] Automation: Reduces the workload of manual data input and processing, and improves efficiency.

[0088] Objectivity: Automation technology reduces the impact of human subjective judgment and improves the objectivity of evaluation.

[0089] Accuracy: The accuracy of optical character recognition technology and word segmentation can improve the accuracy of text information extraction.

[0090] By photographing and scanning the basic images of the basic teaching function evaluation corresponding to each medical teacher, the corresponding evaluation terms are obtained, and text information is effectively extracted from the basic images to provide data support for the subsequent evaluation report generation, which not only improves the efficiency of the evaluation, but also enhances the objectivity and accuracy of the evaluation.

[0091] See also Figure 3 As shown, it is a flow chart of the word segmenter of the present invention screening text scanning information, including:

[0092] Step St1, the term extraction model segments the text scanning information according to semantics to form a number of text words;

[0093] Step St2, sorting the text words according to the number of words in the text to form a preliminary text;

[0094] Step St3, preprocessing the primary selected text to form corresponding text preprocessing data;

[0095] Step St4, the term extraction model receives the text preprocessing data and performs learning to generate corresponding evaluation terms.

[0096] In some possible implementations, if the text scan information is "Teacher A has strong teaching plan writing ability, the teaching plan is neat and clear, the teaching process is very classroom design ability, vivid and easy to understand, the students' classroom feedback is very positive, and the teacher has good teaching reflection ability and can make timely improvements to the classroom content.", the entry extraction model will segment the text scan information according to semantics, and the resulting text vocabulary is "teaching plan writing ability", "strong", "classroom design ability", "vivid and easy to understand", "classroom feedback", "positive", "teaching reflection ability", "make improvements". These text vocabulary are sorted according to the number of words in the text, and the resulting preliminary text is: "teaching plan writing ability", "classroom design ability", "teaching reflection ability", "vivid and easy to understand", "classroom feedback", "make improvements", "strong", "positive".

[0097] If the text scanning information is "Teacher B has strong ability to use teaching tools, the teaching process is vivid, lively and easy to understand, has good bedside teaching ability, and has profound proposition and invigilation ability, covers key test points, and has clear ideas.", the entry extraction model will segment the text scanning information according to semantics, and the resulting text words are "ability to use teaching tools", "strong", "vivid", "lively and easy to understand", "good", "ability to teach by bedside", "profound", "proposition and invigilation ability", and "clear ideas". These text words are sorted according to the number of words in the text, and the resulting preliminary text is: "ability to use teaching tools", "proposition and invigilation ability", "vivid", "lively and easy to understand", "ability to teach by bedside", "clear ideas", "strong", "good", and "profound".

[0098] The term extraction model first performs semantic segmentation on the text scanning information, dividing the continuous text into several independent text words to ensure the semantic integrity of the words.

[0099] Preprocess the preliminary text, which includes removing stop words, stemming, and other steps to form text preprocessing data. Preprocessing is a common step in text analysis, which aims to reduce the complexity of data and improve the efficiency and accuracy of subsequent processing.

[0100] The term extraction model receives preprocessed text data and learns it. This learning process involves machine learning algorithms. Finally, the model generates corresponding evaluation terms, which will be used to generate evaluation reports.

[0101] The advantages of this process are:

[0102] Semantic accuracy: Semantic segmentation is performed through the term extraction model to ensure the semantic integrity of the vocabulary.

[0103] Automated processing: Automated text processing reduces manual intervention and improves efficiency.

[0104] Preprocessing optimization: The preprocessing step helps improve the learning efficiency and accuracy of the model.

[0105] Machine learning: Using machine learning technology, the model can be continuously optimized to improve the accuracy of term extraction.

[0106] By cutting and sorting the text scanning information according to semantics, preprocessing the preliminary text, using the term extraction model to learn the text preprocessing data, and generating the corresponding evaluation terms, it is possible to extract, process and generate terms for teaching evaluation from the original text scanning information. This process not only involves text mining and natural language processing technology, but also includes the application of machine learning, which improves the accuracy and efficiency of evaluation. Through the application of these technologies, valuable information can be effectively extracted from a large amount of text data, providing a scientific and objective basis for teaching evaluation.

[0107] Specifically, the steps of preprocessing the primary text include:

[0108] Perform text cleaning on the preliminary selected text to form corresponding text cleaning data, where:

[0109] Text cleaning is to remove text words below the matching threshold in the preliminary text;

[0110] The matching threshold is the minimum standard for the matching degree between text words and evaluation types and / or evaluation results;

[0111] The text cleaning data is standardized to form the corresponding text preprocessing data, where:

[0112] The standardization process is to cut the text cleaning data according to the standard sampling rate;

[0113] The standard sampling rate is a sampling rate that can be recognized by the term extraction model, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0114] In a specific implementation, when the standard sampling rate is between 160 and 180 terms per second, the term extraction model has the best effect on the generation of evaluation terms. The standard sampling rate is usually set to 170 terms per second.

[0115] Purpose of text cleaning: remove text words from the preliminary text that have a match below a preset threshold with the review type and / or review result. By setting a match threshold, words that do not meet the minimum match criteria are automatically removed. This threshold is pre-defined to ensure that only words relevant to the review are retained.

[0116] The purpose of standardization is to cut the cleaned text data according to a certain standard sampling rate to adapt to the recognition requirements of the term cutting model. Cut the cleaned text data according to the standard sampling rate to ensure that the term cutting model can recognize and extract the evaluation terms with the best effect. The "standard sampling rate" here refers to the rate at which the term cutting model can process data most effectively.

[0117] The purpose of determining the best sampling rate is to obtain the best entry generation effect. Setting the standard sampling rate to 170 per second is a compromise choice that ensures both processing speed and accuracy of entry recognition.

[0118] The advantages of the pre-processing process are:

[0119] Improve efficiency: Through automatic cleaning and standardization, unnecessary data processing is reduced and processing efficiency is improved.

[0120] Improve accuracy: By setting the matching threshold and the optimal sampling rate, the recognition accuracy of the term extraction model is improved.

[0121] Flexibility: The matching threshold and sampling rate can be adjusted according to different application scenarios and requirements to meet different evaluation needs.

[0122] By cleaning and standardizing the preliminary texts, corresponding text preprocessing data is formed, which is used for data preparation in natural language processing and text mining. This ensures the quality of the data and the accuracy of the model, effectively extracts valuable information from large amounts of text data, and provides a scientific and objective basis for teaching evaluation.

[0123] See also Figure 4 As shown, it is a flow chart of the present invention for training the term extraction model, including:

[0124] Step Sp1, iteratively optimize the term extraction model according to the text preprocessing data set until the loss value converges to a preset value, where:

[0125] The text preprocessing data set includes text preprocessing data formed by standardizing each text cleaning data;

[0126] Step Sp2, testing the current term extraction model through the text preprocessing data set;

[0127] Step Sp3, when the test result meets the preset test result, the parameters of the term extraction model are saved.

[0128] The purpose of setting up iterative optimization of the term extraction model is to train the term extraction model using the text preprocessing dataset and continuously iterate and optimize until the model's loss value converges to the preset value. In this step, the model adjusts its parameters by learning from the data in the text preprocessing dataset. The loss value is an indicator that measures the difference between the model's prediction and the actual result. The model parameters are continuously adjusted through optimization algorithms (such as gradient descent) to minimize the loss value. The text preprocessing dataset provides the model with the data required for training.

[0129] The purpose of testing the term extraction model: After the model is trained to a certain extent, the current term extraction model is tested using the text preprocessing dataset to evaluate its performance. The testing phase is a key step in verifying the performance of the model. By applying the model to the test dataset, the model's performance indicators such as accuracy and recall can be evaluated.

[0130] The purpose of saving model parameters: If the test results meet the preset test result standards, then the parameters of the term extraction model are saved, which marks the completion of model training. When the performance of the model on the test set meets or exceeds the preset performance standards, the model parameters are saved for future use or further deployment. These parameters are the knowledge learned by the model and are the key to the model's ability to perform effective term extraction.

[0131] The advantages of this training process are:

[0132] Automation: Through automated iterative optimization and testing, manual intervention is reduced and training efficiency is improved.

[0133] Performance guarantee: The preset loss value and test result standard ensure that the performance of the model reaches a certain level.

[0134] Flexibility: The preset values ​​can be adjusted according to different application scenarios and requirements to meet different evaluation needs.

[0135] By training the term extraction model, the term extraction model can be effectively trained and optimized to achieve reliable performance to ensure its accuracy and reliability in practical applications.

[0136] Specifically, the steps for filling the evaluation catalog into the evaluation report include:

[0137] Extract keywords from evaluation terms and divide standard indicator features;

[0138] Classify the evaluation terms according to the standard indicator characteristics to form a corresponding evaluation catalog;

[0139] Fill in the evaluation catalogue in the evaluation report.

[0140] The purpose of extracting keywords from evaluation terms is to extract key information from evaluation terms, and these keywords can represent the core content of the terms. In specific implementations, natural language processing techniques, such as TF-IDF, Word2Vec or other text mining algorithms, are usually used to identify and extract key words from terms.

[0141] The purpose of dividing standard indicator features is to match evaluation terms with predefined standard indicator features based on keywords.

[0142] The purpose of classifying evaluation terms is to classify evaluation terms according to standard indicator characteristics for easy organization and presentation. According to the standard indicator characteristics corresponding to each term, the terms are classified into corresponding categories or evaluation catalogs to ensure that each term can be correctly classified.

[0143] The purpose of forming a corresponding evaluation catalog is to create a structured evaluation catalog to organize and navigate the evaluation report. Arrange the classified evaluation terms to form an evaluation catalog. This catalog can be a part of the document or a separate file to guide the writing of the evaluation report.

[0144] Purpose of filling the evaluation catalogue into the evaluation report: Integrate the evaluation catalogue and its contents into the evaluation report to provide detailed evaluation results. Fill in the evaluation catalogue in the corresponding section of the evaluation report to ensure that each evaluation term has a corresponding location and context. This may involve manual editing or the use of automated tools to ensure the accuracy and readability of the evaluation report.

[0145] The advantages of this process are:

[0146] Structuring: By extracting keywords and classification terms, the evaluation report is made more structured and easier to understand.

[0147] Accuracy: Ensure the accurate match between evaluation terms and standard indicator characteristics, thus improving the accuracy of the evaluation.

[0148] Efficiency: Automated classification and catalog generation can improve the efficiency of evaluation report writing.

[0149] By extracting the keywords of the evaluation terms, dividing the standard indicator characteristics, and classifying the evaluation terms according to the standard indicator characteristics, a corresponding evaluation catalog is formed and filled into the evaluation report, thereby ensuring the accuracy, completeness and usefulness of the evaluation report, and providing a detailed evaluation of the basic teaching functions of medical teachers, which not only improves the efficiency of the evaluation, but also enhances the objectivity and systematicness of the evaluation.

[0150] Specifically, the steps of extracting keywords from evaluation entries include:

[0151] The keyword extraction model receives and saves standard indicator features;

[0152] Count the frequency of occurrence of keywords and determine the extraction priority of keywords according to the frequency of occurrence.

[0153] Among them, a frequency threshold is set in the keyword extraction model;

[0154] The keyword extraction model extracts keywords from the evaluation entries according to the extraction priority.

[0155] The purpose of receiving and saving standard indicator features is to ensure that the keyword extraction model can understand which standard indicator features are associated with the evaluation terms. The model receives a pre-defined set of standard indicator features and saves them in the model's storage for use in the keyword extraction process.

[0156] The purpose of counting the frequency of occurrence of keywords is to determine their importance by counting the number of times each word appears in the evaluation terms. The model traverses all the evaluation terms and counts the number of times each word appears.

[0157] The purpose of determining the extraction priority of keywords is to determine which words are more likely to be important keywords based on the frequency of occurrence of keywords. The model sorts the frequency of occurrence of each word based on statistical results to determine the extraction priority of keywords. High-frequency words are more likely to be extracted as keywords.

[0158] The advantages of this process are:

[0159] Automation: Through automated keyword extraction, manual intervention is reduced and efficiency is improved.

[0160] Objectivity: Determining keywords through statistical methods reduces the influence of subjective judgment and improves the objectivity of evaluation.

[0161] Flexibility: The frequency threshold can be adjusted according to different evaluation terms and standard indicator characteristics to meet different evaluation needs.

[0162] Specifically, when the occurrence frequency of a keyword is greater than a frequency threshold, the priority of the keyword is determined as a priority extraction, and when the occurrence frequency of a keyword is less than the frequency threshold, the priority of the keyword is determined as a normal extraction.

[0163] Determine a standard to distinguish the importance of keywords. A frequency threshold is preset in the keyword extraction model. This threshold is the benchmark used by the model to determine whether a keyword is important. Compare the frequency of occurrence of keywords with the preset threshold to determine the extraction priority of keywords. When the frequency of occurrence of keywords is greater than the frequency threshold, the priority of these keywords is determined as "priority extraction", which means that these keywords will be considered first in the subsequent evaluation term processing because they are considered to be more important. When the frequency of occurrence of keywords is less than the frequency threshold, the priority of these keywords is determined as "normal extraction", which means that although these keywords are also extracted, their importance is relatively low and they may be placed in a secondary position in the evaluation term processing.

[0164] In some possible implementations, the frequency threshold is set to 5 times, the frequency of keyword A "classroom design ability" is 6 times, which is greater than the frequency threshold, and the priority of keyword A is determined to be first extracted, and the frequency of keyword B "vivid and easy to understand" is 4 times, which is less than the frequency threshold, and the priority of keyword B is determined to be ordinary extraction. When extracting keywords A and B, the extraction order is: keyword A>keyword B.

[0165] By extracting keywords from evaluation entries and comparing the frequency of keyword occurrence with the frequency threshold, the keyword extraction model can effectively extract keywords from evaluation entries based on the frequency of keyword occurrence and the preset frequency threshold, which facilitates the generation of evaluation reports and the analysis of teaching evaluation.

[0166] Specifically, the autocompleter classifies keywords according to classification criteria, among which,

[0167] Classification criteria include the semantics, part of speech and / or contextual relevance of the keywords.

[0168] Specifically, the classified keywords are matched with corresponding parts in the evaluation catalog, and based on the matching results, the keywords are automatically filled into the corresponding parts of the evaluation report.

[0169] By matching the classified keywords with the corresponding parts in the evaluation catalog, the keywords are automatically filled into the corresponding parts of the evaluation report, so that the automatic filler can effectively classify the keywords and fill them into the evaluation report, thereby improving the efficiency and accuracy of evaluation report generation.

[0170] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0171] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating a basic teaching function evaluation report for medical teachers, characterized in that: include: Photograph and scan the basic images for evaluating the basic teaching skills of each medical teacher, and obtain the evaluation terms for the basic teaching skills of each medical teacher based on the basic images; Generate several standard indicator features in the evaluation terms and fill them into the evaluation report as the evaluation catalog, where: When a new evaluation term appears, the corresponding indicator feature is generated; The standard indicator features include the evaluation type and evaluation result of the evaluation term, and, Use semantic recognition to merge several indicator features and generate corresponding standard indicator features; The extractor extracts the keywords in the evaluation terms according to the standard indicator characteristics, wherein: The extractor is provided with a keyword extraction model; The automatic filler classifies the keywords, corresponds to the evaluation catalog, and automatically fills them into the evaluation report; The evaluation report generated by the automatic filler is related to the corresponding basic image.

2. The method for generating a teaching basic function evaluation report for medical teachers according to claim 1, characterized in that: The steps to obtain evaluation terms include: The corresponding basic teaching function evaluation of each medical teacher is photographed to form a corresponding basic image; Performing text scanning on the basic image to obtain text scanning information corresponding to the teaching basic functional ability evaluation; The word segmenter screens the text scanning information to obtain corresponding evaluation terms, wherein: The word segmenter is provided with a word segmentation model for tracking and screening the evaluation words.

3. The method for generating a teaching basic function evaluation report for medical teachers according to claim 2, characterized in that: The steps for the word segmenter to filter the text scan information include: The term extraction model segments the text scanning information according to semantics to form a plurality of text words; Sorting the text words according to the number of words in the text to form a preliminary text; Preprocessing the primary selected text to form corresponding text preprocessing data; The term extraction model receives the text preprocessing data and performs learning to generate corresponding evaluation terms.

4. The method for generating a teaching basic function evaluation report for medical teachers according to claim 3, characterized in that: The steps for preprocessing the preliminary text include: The primary selected text is cleaned to form corresponding text cleaning data, wherein: The text cleaning is to remove text words in the primary selected text that are below a matching threshold; The matching degree threshold is the minimum standard of matching degree between the text vocabulary and the evaluation type and / or the evaluation result; The text cleaning data is standardized to form corresponding text preprocessing data, wherein: The standardization process is to cut the text cleaning data according to a standard sampling rate; The standard sampling rate is a sampling rate that can be recognized by the term extraction model, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

5. The method for generating a teaching basic function evaluation report for medical teachers according to claim 4, characterized in that: The steps for training the term extraction model include: The term extraction model is iteratively optimized according to the text preprocessing data set until the loss value converges to a preset value, wherein: The text preprocessing data set includes text preprocessing data formed by standardizing each text cleaning data; Testing the current term extraction model using the text preprocessing data set; When the test result meets the preset test result, the parameters of the term extraction model are saved.

6. The method for generating a teaching basic function evaluation report for medical teachers according to claim 5, characterized in that: The steps for filling the evaluation report with the evaluation catalog include: Extracting keywords of the evaluation terms and dividing the standard indicator features; Classifying the evaluation terms according to the standard indicator characteristics to form a corresponding evaluation catalog; Fill the evaluation catalogue into the evaluation report.

7. The method for generating a teaching basic function evaluation report for medical teachers according to claim 6, characterized in that: The steps of extracting keywords from evaluation entries include: The keyword extraction model receives and stores the standard indicator features; Counting the occurrence frequency of the keywords, and determining the extraction priority of the keywords according to the occurrence frequency, Wherein, a frequency threshold is set in the keyword extraction model; The keyword extraction model extracts keywords from the evaluation terms according to the extraction priority.

8. The method for generating a teaching basic function evaluation report for medical teachers according to claim 7, characterized in that: When the occurrence frequency of the keyword is greater than the frequency threshold, the priority of the keyword is determined as priority extraction; when the occurrence frequency of the keyword is less than the frequency threshold, the priority of the keyword is determined as normal extraction.

9. The method for generating a teaching basic function evaluation report for medical teachers according to claim 8, characterized in that: The automatic filler classifies the keywords according to the classification criteria, wherein: The classification criteria include the semantics, part of speech and / or context relevance of the keyword.

10. The method for generating a teaching basic function evaluation report for medical teachers according to claim 9, characterized in that: The classified keywords are matched with corresponding parts in the evaluation catalog, and according to the matching results, the keywords are automatically filled into corresponding parts of the evaluation report.

Images