Classroom teaching mode construction method and system, electronic device and storage medium

Abstract

The present application discloses a method and system for constructing a classroom teaching model, an electronic device and a storage medium, the method comprising: obtaining classroom teaching process data; the classroom teaching process data comprises curriculum standard data, teaching syllabus data and classroom dialogue data; subject extraction processing is performed on the classroom teaching process data to determine a subject set; target mining processing is performed on the curriculum standard data and the teaching syllabus data to determine a teaching target set; event analysis is performed on the classroom dialogue data through a large language model to determine an event set; and a classroom teaching model diagram is established and displayed based on the subject set, the teaching target set and the event set. The embodiments of the present application are conducive to improving the accuracy and efficiency of classroom teaching model diagram construction. The present application can be widely used in the field of educational artificial intelligence technology.

Description

Technical Field

[0001] The present application relates to the field of educational artificial intelligence technology, and in particular to a classroom teaching model construction method and system, electronic equipment and storage medium. Background Art

[0002] In the related art, the construction of classroom teaching model mainly relies on manual processing mode, through the arrangement and classification of teaching data by relevant personnel, the classroom teaching model is formed to optimize the teaching process of teachers and related teaching workers. In some embodiments, part of the information extraction process can also be achieved by intelligent means, however, the overall process of classroom teaching model construction cannot be automated and intelligent, which leads to low efficiency of the construction process; it depends on the knowledge level and sophistication of the builder, and the construction accuracy is not high. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose an efficient classroom teaching model construction method and system, electronic device and storage medium.

[0004] To achieve the above-mentioned purpose, one aspect of an embodiment of the present application proposes a method for constructing a classroom teaching model, the method comprising: obtaining classroom teaching process data; the classroom teaching process data comprises curriculum standard data, syllabus data and classroom dialogue data; subject extraction processing is performed on the classroom teaching process data to determine a subject set; target mining processing is performed on the curriculum standard data and the syllabus data to determine a teaching target set; event analysis is performed on the classroom dialogue data through a large language model to determine an event set; and a classroom teaching model diagram is established and displayed based on the subject set, the teaching target set and the event set. The embodiment of the present application determines the subject set, the teaching target set and the event set by processing classroom teaching data, thereby realizing the automatic construction of a classroom teaching model diagram. The embodiment of the present application is conducive to improving the accuracy and efficiency of classroom teaching model diagram construction.

[0005] In some embodiments, the method provided by the embodiments of the present application, the subject extraction processing of the classroom teaching process data to determine the subject set includes:

[0006] Extract keywords from the curriculum standard data to determine a subject word set;

[0007] Performing word segmentation processing on the teaching syllabus data and the classroom dialogue data to determine a first word segmentation set;

[0008] Performing part-of-speech tagging on each word in the first word segmentation set, and selecting a first keyword set belonging to nouns and verbs;

[0009] Predicting the teaching syllabus data and the classroom conversation data through a first named entity recognition model to obtain a second keyword set;

[0010] Performing a union process on the first keyword set and the second keyword set to determine a preliminary screening keyword set;

[0011] The elements in the preliminary screening keyword set that are identical to the elements in the subject word set are screened out to form a target subject word set; the elements in the preliminary screening keyword set that are unrelated to the elements in the subject word set are screened out to form a target free word set; the subject set includes the target subject word set.

[0012] In some embodiments, the method provided by the embodiments of the present application further includes:

[0013] Performing hyponym and hyponym expansion on each element in the subject word set, and putting the hypernyms and hyponyms after the hyponym and hyponym expansion into the subject-related word set;

[0014] Putting synonyms and similar words of each element in the subject word set into the subject-related word set;

[0015] Elements in the target free word set that are associated with elements in the subject-related word set are screened out to form a target keyword set; the subject set includes the target keyword set.

[0016] In some embodiments, the method provided in the embodiments of the present application, the target mining process is performed on the course standard data and the teaching syllabus data to determine the teaching target set, including:

[0017] Extracting target words from the curriculum standard data to determine a process target word set and a result target word set;

[0018] Performing word segmentation processing on the teaching syllabus data to determine a second word segmentation set;

[0019] Performing part-of-speech tagging on each word in the second word segmentation set, and selecting a first target word set that is a verb;

[0020] Predicting the teaching syllabus data through a second named entity recognition model to obtain a second target word set;

[0021] performing a union process on the first target word set and the second target word set to determine a preliminary screening target word set;

[0022] The elements in the initial screening target word set that are the same as the elements in the process target word set are screened out to form a process requirement word set; the elements in the initial screening target word set that are the same as the elements in the result target word set are screened out to form a result requirement word set; the teaching target set includes the process requirement word set and the result requirement word set.

[0023] In some embodiments, the method provided by the embodiments of the present application, wherein the classroom conversation data is subjected to event analysis through a large language model to determine an event set, comprises:

[0024] Slicing the classroom conversation data to obtain a number of block data;

[0025] Inputting a plurality of said block data into a first language model to obtain a learning process event;

[0026] Inputting the plurality of block data and corresponding encoding records into a second language model to obtain an interaction process event sequence;

[0027] The block data and the encoding record corresponding to each interactive process event element in the interactive process event sequence are input into a third language model to obtain evaluation information.

[0028] In some embodiments, the method provided by the embodiments of the present application further includes:

[0029] Obtaining the number of conversation rounds of classroom conversation data; and performing equal slicing processing on the classroom conversation data according to the number of conversation rounds and a preset number of blocks to obtain a plurality of block data;

[0030] or,

[0031] Constructing an introductory phrase set and a transition phrase set; obtaining the last sentence of the current dialogue round and the first sentence of the next dialogue round; calculating the similarity between the last sentence and each transition phrase in the transition phrase set to determine a first similarity; calculating the similarity between the first sentence and each introductory phrase in the introductory phrase set to determine a second similarity; if the first similarity is greater than or equal to a first threshold, and the second similarity is greater than or equal to a second threshold, segmenting the conversation using the last sentence and the first sentence as a boundary.

[0032] In some embodiments, the method provided by the embodiment of the present application, the classroom teaching mode diagram includes a subject part, a teaching objective part and a learning process part, the subject part, the teaching objective part and the learning process part are sequentially connected and displayed, and the method further includes:

[0033] The elements in the target subject word set are directly displayed in the subject part, and the elements in the target keyword set are extendedly displayed in the subject part; the subject set includes the target subject word set and the target keyword set;

[0034] The demand elements in the process demand word set and the result demand word set are directly displayed in the teaching goal part, and the teaching goal description sentence is extended and displayed in the teaching goal part; the teaching goal set includes the process demand word set and the result demand word set; the teaching goal description sentence is a sentence in the teaching syllabus data corresponding to the demand element;

[0035] The learning process events are directly displayed in the learning process event area of ​​the learning process part, the interactive process event sequence is directly displayed in the interactive process event area of ​​the learning process part, and the evaluation information is extendedly displayed in the learning process part; the event set includes the learning process events, the interactive process event sequence and the evaluation information.

[0036] To achieve the above purpose, another aspect of the embodiment of the present application proposes a classroom teaching mode construction system, the system comprising:

[0037] The first module is used to obtain classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data;

[0038] The second module is used to perform topic extraction processing on the classroom teaching process data to determine a topic set;

[0039] The third module is used to perform target mining processing on the course standard data and the teaching syllabus data to determine the teaching target set;

[0040] The fourth module is used to perform event analysis on the classroom dialogue data through a large language model to determine an event set;

[0041] The fifth module is used to establish and display a classroom teaching model diagram based on the subject set, the teaching goal set and the event set.

[0042] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0043] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0044] The embodiments of the present application include at least the following beneficial effects: The method provided by the present application includes: obtaining classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data; subject extraction processing is performed on the classroom teaching process data to determine the subject set; target mining processing is performed on the curriculum standard data and the teaching syllabus data to determine the teaching target set; event analysis is performed on the classroom dialogue data through a large language model to determine the event set; according to the subject set, the teaching target set and the event set, a classroom teaching model diagram is established and displayed. The embodiments of the present application can automatically construct a classroom teaching model diagram by processing classroom teaching data to determine the subject set, the teaching target set and the event set. The embodiments of the present application are conducive to improving the accuracy and efficiency of classroom teaching model diagram construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flowchart of an embodiment of the method for constructing a classroom teaching model provided by the present application;

[0046] Figure 2 It is a flow chart of another embodiment of the classroom teaching mode construction method provided by the present application;

[0047] Figure 3 This is an interface effect diagram of an embodiment of the classroom teaching mode diagram provided by this application;

[0048] Figure 4 It is a structural diagram of a classroom teaching mode construction system provided in an embodiment of the present application;

[0049] Figure 5 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0051] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0052] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0054] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0055] Subject headings: refers to the vocabulary used to represent a specific subject in literature retrieval, information retrieval or classification systems. Subject headings are usually standardized and universal so that users can find relevant information quickly and accurately.

[0056] Free words: refers to words that are not restricted by specific subject terms in literature retrieval, information retrieval or classification systems. Free words can help users find other information related to keywords and improve the accuracy and comprehensiveness of retrieval.

[0057] Hypernym: refers to a word with a high degree of generality in the semantic hierarchy. A hypernym can be used to represent a concept or category, while also including the specific concept or category represented by its hyponym. For example, "animal" is a hypernym, while "mammal", "bird", etc. are its hyponyms.

[0058] Hyponym: refers to a word with a lower generality in the semantic hierarchy. A hyponym is used to represent a more specific concept or category that is included in the concept or category represented by its hypernym. For example, "mammal" is a hyponym, while "bird", "cat", etc. are its hypernyms.

[0059] Synonyms: words with the same or similar meanings. Synonyms can help users express the same meaning in different contexts, increasing the richness of language and the accuracy of expression. For example, "beautiful" and "pretty" are a pair of synonyms.

[0060] Similar words: words with similar or related meanings in semantics. Similar words can help users expand their search scope and find more information related to keywords. For example, "apple" and "banana" are a pair of similar words because they both belong to the category of fruit.

[0061] Word segmentation: The process of dividing a continuous text sequence into a series of discrete words.

[0062] Part-of-speech tagging: The process of assigning a part-of-speech tag to each word. Part-of-speech tags indicate the grammatical function of a word in a sentence, such as noun, verb, adjective, etc. Part-of-speech tagging helps understand the structure and semantics of a sentence.

[0063] Entity extraction: Identify and extract entities with specific meanings from text, such as names of people, places, and organizations. Entity extraction is an important task in fields such as information retrieval and knowledge graph construction.

[0064] Big Language Model: A natural language processing model based on deep learning that is trained with large amounts of text data and can generate coherent and natural text. Big Language Model can be used for a variety of tasks such as machine translation, text summarization, and question-answering systems.

[0065] Information extraction is an important branch in the field of artificial intelligence and natural language processing. Its core goal is to automatically extract structured information from unstructured text data. In the field of education, it is usually the process of extracting specific events or factual information from natural language texts in educational scenarios, including the identification and classification of elements such as knowledge points, concepts, themes, and theorems. In the present invention, information extraction is used to extract key text content elements from classroom teaching process data such as curriculum standards, teaching syllabuses, and classroom dialogues, thereby providing data support for the construction of classroom teaching models.

[0066] Named entity recognition is a key task in the field of natural language processing and is also the basis of information extraction. Its main goal is to identify entities with specific meanings from text and classify them into predetermined categories, such as names, places, names of institutions, dates, times, monetary amounts, etc. This technology plays a vital role in understanding and organizing large-scale text data. In the present invention, named entity recognition is used to identify entities such as teaching topics and objectives from classroom teaching text data to provide support for the subsequent generation of teaching model diagrams.

[0067] Existing classroom teaching model construction technology is difficult to achieve the combination of automation and visualization. The present invention can automatically and real-time construct the classroom teaching model, and perform all-round intelligent perception and high-level restoration of the classroom teaching process, helping teachers, teaching researchers and other educators to understand the manifestation and evolution of the classroom teaching process from a macro level, and gain insight into the implicit processes of classroom teaching such as thinking advancement, problem exploration laws, and cognitive evolution laws from a micro level. It presents classroom interactions involving multiple subjects in the form of visual analysis, promotes the evidence, precision and scale of classroom teaching research, and provides guidance for effectively identifying the process characteristics of classroom teaching and constructing high-quality and efficient classrooms.

[0068] The classroom teaching model construction method provided in the embodiment of the present application relates to the field of educational artificial intelligence technology. The classroom teaching model construction method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server, the server can also be a node server in the blockchain network; the software can be an application that implements the classroom teaching model construction method, etc., but is not limited to the above forms.

[0069] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0071] Figure 1 It is an optional flow chart of the classroom teaching mode construction method provided in the embodiment of the present application; Figure 1 The method may include but is not limited to steps S100 to S400.

[0072] Step S100, obtaining classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data;

[0073] Step S200, performing topic extraction processing on the classroom teaching process data to determine a topic set;

[0074] Step S300, performing target mining processing on the course standard data and the teaching syllabus data to determine a teaching target set;

[0075] Step S400, performing event analysis on the classroom conversation data through a large language model to determine an event set;

[0076] Step S500, establishing and displaying a classroom teaching model diagram according to the subject set, the teaching objective set and the event set.

[0077] The subject extraction process of the embodiment of the present application can be performed by a model with relevant functions of artificial intelligence. Subject extraction is used to determine the subjects required for the construction of the classroom teaching model based on the classroom teaching process data. Similarly, target mining processing is used to determine the targets required for the construction of the classroom teaching model, and event analysis is used to determine the events required for the construction of the classroom teaching model. This application does not limit the specific technical form adopted by the above processing.

[0078] The embodiment of the present invention uses classroom teaching process data such as curriculum standards, teaching outlines, classroom dialogues, etc. as the data source for constructing the classroom teaching model. According to the implementation path of "teaching topic extraction - teaching goal mining - teaching event analysis - teaching model diagram generation", important model elements such as themes, goals, events, etc. required for classroom teaching model construction are extracted, mined and analyzed, and finally combined to generate a teaching model diagram reflecting the classroom teaching process.

[0079] The method provided in the embodiment of the present application can be applied to the fields of educational artificial intelligence and educational big data processing technology, especially in front-line classroom teaching scenarios. It can be applied to PC-side tools or software, Web application systems, mobile application software, applets and other software carriers related to classroom teaching monitoring and analysis, and can also be integrated into teaching terminal hardware devices as embedded software, including but not limited to classroom whiteboard equipment, learning machines, etc., with teachers, teaching researchers and other educators as the main target groups, providing services such as visualization analysis and evaluation of classroom teaching model construction.

[0080] In some embodiments, the method provided by the embodiments of the present application, the subject extraction processing of the classroom teaching process data to determine the subject set includes:

[0081] Extract keywords from the curriculum standard data to determine a subject word set;

[0082] Performing word segmentation processing on the teaching syllabus data and the classroom dialogue data to determine a first word segmentation set;

[0083] Performing part-of-speech tagging on each word in the first word segmentation set, and selecting a first keyword set belonging to nouns and verbs;

[0084] Predicting the teaching syllabus data and the classroom conversation data through a first named entity recognition model to obtain a second keyword set;

[0085] Performing a union process on the first keyword set and the second keyword set to determine a preliminary screening keyword set;

[0086] The elements in the preliminary screening keyword set that are identical to the elements in the subject word set are screened out to form a target subject word set; the elements in the preliminary screening keyword set that are unrelated to the elements in the subject word set are screened out to form a target free word set; the subject set includes the target subject word set.

[0087] In some possible implementations, the subject word set in the embodiment of the present application is used to represent knowledge points related to the curriculum standard. The first keyword set is used to represent a word set related to knowledge, and the second keyword set is used to represent a word set related to objective common sense.

[0088] In some embodiments, the method provided by the embodiments of the present application further includes:

[0089] Performing hyponym and hyponym expansion on each element in the subject word set, and putting the hypernyms and hyponyms after the hyponym and hyponym expansion into the subject-related word set;

[0090] Putting synonyms and similar words of each element in the subject word set into the subject-related word set;

[0091] Elements in the target free word set that are associated with elements in the subject-related word set are screened out to form a target keyword set; the subject set includes the target keyword set.

[0092] In some possible implementations, refer to Figure 2 As shown, the teaching topic extraction process provided by the embodiment of the present application can be as follows:

[0093] Step S11, manually extracting the keywords of the knowledge points appearing in the course standard text to obtain a subject word set;

[0094] Step S12: construct a knowledge base for each subject word in the subject word set and review it by experts to obtain a hypernym set, a hyponym set, a synonym set, a similar word set, etc., wherein: a hypernym is a free word with a broader concept extension of the subject word, a hyponym is a free word with a narrower concept connotation of the subject word, a synonym is a free word with the same meaning as the subject word, and a similar word is a free word belonging to the same category or category as the subject word;

[0095] Step S13, segmenting the syllabus text and the classroom dialogue text to obtain a segmentation result set;

[0096] Step S14: perform part-of-speech tagging on each word in the word segmentation result set to obtain a part-of-speech tagging result set;

[0097] Step S15: Screen the words belonging to nouns and verbs in the part-of-speech tagging result set to obtain a first keyword set, wherein the words in the first keyword set usually represent a specific, atomic, and generally indivisible knowledge point, including but not limited to its basic concepts, principles, and methods;

[0098] Step S16: Use a named entity recognition model (such as CRF) to perform entity extraction on the syllabus text and the classroom dialogue text to obtain a second keyword set, wherein the words in the second keyword set usually represent mutually distinguishable objective objects or abstract concepts existing in an objective world, and are generally entities with specific meanings, including but not limited to names of people, places, institutions, and proper nouns;

[0099] Step S17, taking a union of the first keyword set and the second keyword set to obtain a preliminary screening keyword set;

[0100] Step S18, determine whether each word in the primary screening keyword set appears in the subject word set, if so, it is assigned to the target subject word set, otherwise it is assigned to the target free word set;

[0101] Step S19: Search each free word in the target free word set in the aforementioned hypernym set, hyponym set, synonym set, similar word set, etc. to determine whether there is a subject word associated with it in the target subject word set. If so, it is included in the target keyword set.

[0102] In some embodiments, the method provided in the embodiments of the present application, the target mining process is performed on the course standard data and the teaching syllabus data to determine the teaching target set, including:

[0103] Extracting target words from the curriculum standard data to determine a process target word set and a result target word set;

[0104] Performing word segmentation processing on the teaching syllabus data to determine a second word segmentation set;

[0105] Performing part-of-speech tagging on each word in the second word segmentation set, and selecting a first target word set that is a verb;

[0106] Predicting the teaching syllabus data through a second named entity recognition model to obtain a second target word set;

[0107] performing a union process on the first target word set and the second target word set to determine a preliminary screening target word set;

[0108] The elements in the initial screening target word set that are the same as the elements in the process target word set are screened out to form a process requirement word set; the elements in the initial screening target word set that are the same as the elements in the result target word set are screened out to form a result requirement word set; the teaching target set includes the process requirement word set and the result requirement word set.

[0109] In some possible implementations, the process target word set is used to represent the set of action verbs that describe the process, and the result target word set is used to represent the set of action verbs that describe the result. Similarly, the first target word set in the embodiment of the present application is used to represent the word set related to knowledge, and the second target word set is used to represent the word set related to objective common sense. The acquisition process of the teaching target set provided in the embodiment of the present application can be as follows:

[0110] Step S21: Manually extract the words that reflect the process objectives and the result objectives in the curriculum standard text to obtain a process objective word set and a result objective word set, wherein:

[0111] Process goal words are behavioral verbs that describe process goals, including words such as "experience", "feeling", "perception", "exploration" and so on that are clearly stated in the curriculum standards, as well as synonyms or near-synonyms of the above words that have been approved by experts, such as "feel", "try", "understand", "understand", "exploration" and so on.

[0112] The result target word set is the action verbs that describe the result target, including words such as "know", "understand", "master", "apply" and so on that are clearly stated in the curriculum standards, as well as synonyms or near-synonyms of the above words that have been approved by experts, such as "know", "recognize", "apply", "know", "can" and so on;

[0113] Step S22, segmenting the syllabus text to obtain a segmentation result set;

[0114] Step S23, perform part-of-speech tagging on each word in the word segmentation result set to obtain a part-of-speech tagging result set;

[0115] Step S24, filtering the words belonging to verbs in the part-of-speech tagging result set to obtain a first target word set;

[0116] Step S25: Use a named entity recognition model to perform entity extraction on the syllabus text to obtain a second target word set;

[0117] Step S26, taking the union of the first keyword set and the second keyword set to obtain a preliminary screening target word set;

[0118] Step S27, determine whether each word in the initial screening target word set appears in the process target word set, and if so, return it to the process target result word set;

[0119] Step S28: Determine whether each word in the initial screening target word set appears in the result target word set. If so, it is included in the result target word set.

[0120] In some embodiments, the method provided by the embodiments of the present application, wherein the classroom conversation data is subjected to event analysis through a large language model to determine an event set, comprises:

[0121] Slicing the classroom conversation data to obtain a number of block data;

[0122] Inputting a plurality of said block data into a first language model to obtain a learning process event;

[0123] Inputting the plurality of block data and corresponding encoding records into a second language model to obtain an interaction process event sequence;

[0124] The block data and the encoding record corresponding to each interactive process event element in the interactive process event sequence are input into a third language model to obtain evaluation information.

[0125] In some possible implementations, the large language model in the embodiment of the present application includes a first language model, a second language model, and a third language model. It can be understood that the first language model, the second language model, and the third language model can be the same or partially the same model. In addition, the three models can be composed of any model that can perform language processing, and the present application does not make any specific restrictions.

[0126] In some embodiments, the method provided by the embodiments of the present application further includes:

[0127] Obtaining the number of conversation rounds of classroom conversation data; and performing equal slicing processing on the classroom conversation data according to the number of conversation rounds and a preset number of blocks to obtain a plurality of block data;

[0128] or,

[0129] Constructing an introductory phrase set and a transition phrase set; obtaining the last sentence of the current dialogue round and the first sentence of the next dialogue round; calculating the similarity between the last sentence and each transition phrase in the transition phrase set to determine a first similarity; calculating the similarity between the first sentence and each introductory phrase in the introductory phrase set to determine a second similarity; if the first similarity is greater than or equal to a first threshold, and the second similarity is greater than or equal to a second threshold, segmenting the conversation using the last sentence and the first sentence as a boundary.

[0130] In some possible implementations, the process of determining the first similarity in the embodiments of the present application is as follows: similarity is calculated between the last sentence and each transition word in the transition word set, the calculation results are sorted from large to small or from small to large, and the value with the largest similarity is taken as the first similarity.

[0131] Exemplarily, the process of determining the event set provided by the present application may be as follows:

[0132] Step S31: construct an initial event set reflecting the learning process and the interaction process, which is divided into a learning process event set and an interaction process event set, wherein:

[0133] The events in the learning process event set summarize the overall pattern of a certain stage of classroom teaching from a relatively macro and static perspective and are generated by experts, such as "practice", "exploration", "experience", "reflection", "cooperation", "communication", etc.

[0134] The events in the interactive process event set extract and condense the evolution path pattern of a certain stage of classroom teaching from a relatively micro and dynamic perspective, and generate first-level indicators and second-level indicators based on the classroom teaching coding system. For example, the first-level indicators include "basic knowledge", "personal opinions", "analysis and interpretation", "comparison and induction", "transfer and innovation", and "expansion and construction". Among them, "analysis and interpretation" is divided into second-level indicators such as "explanation and argumentation", "example interpretation", and "evaluation".

[0135] Step S32: constructing a set of introductory and transitional phrases for common phased modules of classroom teaching (such as “introduction”, “new teaching”, “consolidation”, and “summary”), where:

[0136] The introductory words in the introductory words set are a sentence or a paragraph of starting words initiated by the teacher in a specific stage module of classroom teaching. They are selected by experts from the corpus of previous famous teachers and can be divided into inspiration, appreciation, praise, reminder, exhortation, encouragement and reflection types according to the type of words.

[0137] The transition words in the transition phrase set are a sentence or a paragraph initiated by the teacher in two consecutive stage modules of classroom teaching, which are used to connect different knowledge points or play a role of connecting the previous and the next. They are composed of the ending words of the previous stage module and the starting words of the subsequent stage module. They are selected by experts from the corpus of previous famous teachers and can be divided into heuristic, exploratory, evaluative, and review-based types according to the type of words.

[0138] Step S33: Slice the turn sequence in the classroom dialogue instance according to different stage modules of classroom teaching to obtain multiple classroom teaching stage blocks, including equal slices and semantic slices, where:

[0139] Equal slicing is to divide the total number of turns in the classroom dialogue text by the number of slices input by the user to get the number of turns in each block and then divide it equally.

[0140] Semantic slicing first traverses the last sentence of each turn of classroom dialogue text and the first sentence of the next turn as units, calculates semantic similarity with each transition word in the transition word set, and determines whether it is the target transition word according to the preset first similarity threshold. If so, continue to calculate semantic similarity between the first sentence of the next turn and each guide word in the guide word set, and determine whether it is the target guide word according to the preset second similarity threshold. If so, segment the text based on the last sentence of the current turn and the first sentence of the next turn as the boundary;

[0141] Step S34, input the teacher-student dialogues of each classroom teaching stage into the large language model for event analysis to obtain the corresponding learning process events;

[0142] Step S35: input the teacher-student dialogues and their coded records of each classroom teaching stage into the large language model for event analysis to obtain the event sequence of the corresponding interaction process;

[0143] Step S36: Input the teacher-student dialogue and its coding record corresponding to each interactive process event element in the interactive process event sequence into the large language model for point-by-point summary and evaluation, and obtain the summary evaluation result of each event in the interactive process event sequence.

[0144] In some embodiments, the method provided by the embodiment of the present application, the classroom teaching mode diagram includes a subject part, a teaching objective part and a learning process part, the subject part, the teaching objective part and the learning process part are sequentially connected and displayed, and the method further includes:

[0145] The elements in the target subject word set are directly displayed in the subject part, and the elements in the target keyword set are extendedly displayed in the subject part; the subject set includes the target subject word set and the target keyword set;

[0146] The demand elements in the process demand word set and the result demand word set are directly displayed in the teaching goal part, and the teaching goal description sentence is extended and displayed in the teaching goal part; the teaching goal set includes the process demand word set and the result demand word set; the teaching goal description sentence is a sentence in the teaching syllabus data corresponding to the demand element;

[0147] The learning process events are directly displayed in the learning process event area of ​​the learning process part, the interactive process event sequence is directly displayed in the interactive process event area of ​​the learning process part, and the evaluation information is extendedly displayed in the learning process part; the event set includes the learning process events, the interactive process event sequence and the evaluation information.

[0148] For example, Figure 3 The display effect diagram of an embodiment shown in the figure, wherein area 310 is the subject part; area 320 is the teaching goal part; area 330 is the learning process event area of ​​the learning process part; area 340 is the interactive process event area of ​​the learning process part; area 350 is the extended display of the relevant part. It can be understood that the extended display in the embodiment of the present application can also be displayed in the manner of triggering the control, that is, displaying, and the present application does not limit the specific form of the extended display.

[0149] Exemplarily, the teaching mode diagram generation process may be as follows:

[0150] Step S41: present all words in the target subject word set and target keyword set generated in the teaching subject extraction phase as pattern elements of the subject part of the teaching pattern diagram, wherein the target subject word is presented as a direct display element (such as Figure 3 A1 to A3 nodes), the target keyword is used as an indirect display element (such as Figure 3 The A3.1 to A3.4 subnodes are displayed under the A3 node, and the edge reflects the relationship between the two words);

[0151] Step S42: directly present all the words in the process target result word set and the result target result word set generated by the teaching target mining link as pattern elements of the target part of the teaching pattern diagram (such as Figure 3 Nodes B1 to B4 of the syllabus), and the teaching objective description sentences in the syllabus are used as indirect display elements (such as Figure 3 The text mark displayed under the B4 node of the

[0152] Step S43: directly present the learning process events generated in the teaching event analysis phase as pattern elements of the learning process event part of the teaching pattern diagram (e.g. Figure 3 CX.1.1 node, X is the stage number), the interactive process event sequence is directly presented as the pattern element of the interactive process event part of the teaching model diagram (such as Figure 3 The summary and evaluation results of each event in the interactive process event sequence are used as indirect display elements of the interactive process event part of the teaching model diagram (such as Figure 3 (the text label displayed under the C2.3.1 node of the ).

[0153] The method provided in the embodiment of the present application includes: obtaining classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data; performing subject extraction processing on the classroom teaching process data to determine the subject set; performing target mining processing on the curriculum standard data and the teaching syllabus data to determine the teaching target set; performing event analysis on the classroom dialogue data through a large language model to determine the event set; establishing and displaying a classroom teaching model diagram based on the subject set, the teaching target set and the event set. The embodiment of the present application can automatically construct a classroom teaching model diagram by processing classroom teaching data to determine the subject set, the teaching target set and the event set. The embodiment of the present application is conducive to improving the accuracy and efficiency of classroom teaching model diagram construction.

[0154] The embodiment of the present application provides a teaching topic extraction process, including the construction of four subject word knowledge bases, namely, hypernym set, hyponym set, synonym set, and similar word set, and the process of obtaining the target subject word set and target keyword set through steps such as word segmentation, part-of-speech tagging, entity extraction, and screening.

[0155] The embodiment of the present application provides a teaching goal mining process, including the construction of a process goal word set and a result goal word set, and the process of obtaining a process goal result word set and a result goal result word set through steps such as word segmentation, part-of-speech tagging, entity extraction, and screening.

[0156] The embodiment of the present application provides an analysis process of teaching events, including the construction of learning process event sets, interactive process event sets, guide language sets, and transition language sets, as well as the process of obtaining the learning process events, interactive process event sequences, and summary evaluation results of each classroom teaching stage block through turn sequence slicing, large language model event analysis, and large language model point summary and evaluation.

[0157] The embodiment of the present application provides a process for generating a teaching model diagram, including a process of visually presenting the results of each link output from integrating teaching topic extraction, teaching goal mining, and teaching event analysis as model elements.

[0158] The embodiment of the present application applies named entity recognition, large language model and other technologies in a step-by-step and gradual manner to extract, mine and analyze important model elements such as themes, goals, events, etc. required for the construction of classroom teaching models, and gradually completes the generation of teaching model diagrams. It reveals the complex thinking chain building process, knowledge construction process and problem exploration process in a visual form, enabling educators to better understand the internal laws, causal chains, behavioral motivations and thinking cognition of the classroom teaching process, and enhance the interpretability and comprehensibility of classroom teaching model construction.

[0159] See also Figure 4 The embodiment of the present application also provides a classroom teaching mode construction system, which can implement the above-mentioned classroom teaching mode construction method, and the system includes:

[0160] The first module 410 is used to obtain classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data;

[0161] The second module 420 is used to perform topic extraction processing on the classroom teaching process data to determine a topic set;

[0162] The third module 430 is used to perform target mining processing on the course standard data and the teaching syllabus data to determine a teaching target set;

[0163] The fourth module 440 is used to perform event analysis on the classroom dialogue data through a large language model to determine an event set;

[0164] The fifth module 450 is used to establish and display a classroom teaching model diagram based on the subject set, the teaching goal set and the event set.

[0165] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0166] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned classroom teaching mode construction method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0167] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0168] See also Figure 5 , Figure 5 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0169] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0170] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the classroom teaching mode construction method of the embodiment of this application;

[0171] Input / output interface 903, used to implement information input and output;

[0172] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0173] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0174] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0175] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned classroom teaching model construction method is implemented.

[0176] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0177] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0178] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0179] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0180] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0182] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0183] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0184] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0185] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0187] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0188] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for constructing a classroom teaching model, characterized in that: The method comprises: Acquire classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data; Performing topic extraction processing on the classroom teaching process data to determine a topic set; Performing target mining processing on the curriculum standard data and the teaching syllabus data to determine a teaching target set; Performing event analysis on the classroom conversation data using a large language model to determine an event set; Establishing and displaying a classroom teaching model diagram according to the subject set, the teaching goal set and the event set; The subject extraction process of the classroom teaching process data to determine the subject set includes: Extract keywords from the curriculum standard data to determine a subject word set; Performing word segmentation processing on the teaching syllabus data and the classroom dialogue data to determine a first word segmentation set; Performing part-of-speech tagging on each word in the first word segmentation set, and selecting a first keyword set belonging to nouns and verbs; Predicting the teaching syllabus data and the classroom conversation data through a first named entity recognition model to obtain a second keyword set; Performing a union process on the first keyword set and the second keyword set to determine a preliminary screening keyword set; The elements in the preliminary screening keyword set that are identical to the elements in the subject word set are screened out to form a target subject word set; the elements in the preliminary screening keyword set that are unrelated to the elements in the subject word set are screened out to form a target free word set; the subject set includes the target subject word set.

2. The method according to claim 1, characterized in that The method further comprises: Performing hyponym and hyponym expansion on each element in the subject word set, and putting the hypernyms and hyponyms after the hyponym and hyponym expansion into the subject-related word set; Putting synonyms and similar words of each element in the subject word set into the subject-related word set; Elements in the target free word set that are associated with elements in the subject-related word set are screened out to form a target keyword set; the subject set includes the target keyword set.

3. The method according to claim 1, characterized in that: The target mining process is performed on the course standard data and the teaching syllabus data to determine the teaching target set, including: Extracting target words from the curriculum standard data to determine a process target word set and a result target word set; Performing word segmentation processing on the teaching syllabus data to determine a second word segmentation set; Performing part-of-speech tagging on each word in the second word segmentation set, and selecting a first target word set that is a verb; Predicting the teaching syllabus data through a second named entity recognition model to obtain a second target word set; performing a union process on the first target word set and the second target word set to determine a preliminary screening target word set; The elements in the initial screening target word set that are the same as the elements in the process target word set are screened out to form a process requirement word set; the elements in the initial screening target word set that are the same as the elements in the result target word set are screened out to form a result requirement word set; the teaching target set includes the process requirement word set and the result requirement word set.

4. The method according to claim 1, characterized in that: The step of performing event analysis on the classroom conversation data through a large language model to determine an event set includes: Slicing the classroom conversation data to obtain a number of block data; Inputting a plurality of said block data into a first language model to obtain a learning process event; Inputting the plurality of block data and corresponding encoding records into a second language model to obtain an interaction process event sequence; The block data and the encoding record corresponding to each interactive process event element in the interactive process event sequence are input into a third language model to obtain evaluation information.

5. The method according to claim 4, characterized in that The method further comprises: Obtaining the number of conversation rounds of classroom conversation data; and performing equal slicing processing on the classroom conversation data according to the number of conversation rounds and a preset number of blocks to obtain a plurality of block data; or, Constructing an introductory phrase set and a transition phrase set; obtaining the last sentence of the current dialogue round and the first sentence of the next dialogue round; calculating the similarity between the last sentence and each transition phrase in the transition phrase set to determine a first similarity; calculating the similarity between the first sentence and each introductory phrase in the introductory phrase set to determine a second similarity; if the first similarity is greater than or equal to a first threshold, and the second similarity is greater than or equal to a second threshold, segmenting the conversation using the last sentence and the first sentence as a boundary.

6. The method according to any one of claims 1 to 5, characterized in that The classroom teaching model diagram includes a subject part, a teaching target part and a learning process part, wherein the subject part, the teaching target part and the learning process part are sequentially connected and displayed, and the method further includes: The elements in the target subject word set are directly displayed in the subject part, and the elements in the target keyword set are extendedly displayed in the subject part; the subject set includes the target subject word set and the target keyword set; The demand elements in the process demand word set and the result demand word set are directly displayed in the teaching goal part, and the teaching goal description sentence is extended and displayed in the teaching goal part; the teaching goal set includes the process demand word set and the result demand word set; the teaching goal description sentence is a sentence in the teaching syllabus data corresponding to the demand element; The learning process events are directly displayed in the learning process event area of ​​the learning process part, the interactive process event sequence is directly displayed in the interactive process event area of ​​the learning process part, and the evaluation information is extendedly displayed in the learning process part; the event set includes the learning process events, the interactive process event sequence and the evaluation information.

7. A classroom teaching model construction system, characterized in that: The system comprises: The first module is used to obtain classroom teaching process data; the classroom teaching process data includes curriculum standard data, teaching syllabus data and classroom dialogue data; The second module is used to perform topic extraction processing on the classroom teaching process data to determine a topic set; The third module is used to perform target mining processing on the course standard data and the teaching syllabus data to determine the teaching target set; The fourth module is used to perform event analysis on the classroom dialogue data through a large language model to determine an event set; A fifth module is used to establish and display a classroom teaching model diagram according to the subject set, the teaching goal set and the event set; The second module is used for performing topic extraction processing on the classroom teaching process data to determine a topic set, including: Extract keywords from the curriculum standard data to determine a subject word set; Performing word segmentation processing on the teaching syllabus data and the classroom dialogue data to determine a first word segmentation set; Performing part-of-speech tagging on each word in the first word segmentation set, and selecting a first keyword set belonging to nouns and verbs; Predicting the teaching syllabus data and the classroom conversation data through a first named entity recognition model to obtain a second keyword set; Performing a union process on the first keyword set and the second keyword set to determine a preliminary screening keyword set; The elements in the preliminary screening keyword set that are identical to the elements in the subject word set are screened out to form a target subject word set; the elements in the preliminary screening keyword set that are unrelated to the elements in the subject word set are screened out to form a target free word set; the subject set includes the target subject word set.

8. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images