Text quality evaluation system of education database

Abstract

The invention discloses a text quality evaluation system of an education database, which relates to the technical field of education and comprises an education knowledge base, a text quality evaluation module and a fusion analysis module, the text quality evaluation module is connected with the education knowledge base and the fusion analysis module; the text quality evaluation module is used for obtaining content feature data corresponding to the to-be-evaluated content in the education knowledge base, evaluating the content accuracy degree and the teaching adaptability degree of the to-be-evaluated content from multiple dimensions, and obtaining content accuracy data and teaching adaptability data; the content accuracy data and the teaching fitness data are sent to the fusion analysis module; and the fusion analysis module is used for performing fusion analysis on the content accuracy data and the teaching fitness data to obtain a quality evaluation result of the to-be-evaluated content. According to the invention, the evaluation result is more in line with the real teaching condition, the content quality of the evaluated target teaching content is ensured, and the overall teaching efficiency is improved.

Description

A text quality assessment system for educational databases Technical Field

[0001] This application relates to the field of educational technology, and more particularly to a text quality assessment system for educational databases. Background Technology

[0002] An educational knowledge base is a structured, computable, and scalable collection of knowledge in the field of education. It systematically organizes information such as subject knowledge, teaching methods, learning theories, curriculum standards, typical problems, problem-solving strategies, and student cognitive models, providing reliable, accurate, and reasonable knowledge support for intelligent education systems (such as adaptive learning platforms, AI teaching assistants, automatic question generation systems, and large-scale educational models).

[0003] Currently, the quality assessment of educational knowledge bases mainly relies on a one-time static evaluation based on superficial indicators such as keyword density and text readability in the teaching content, thereby obtaining the evaluation results of the educational knowledge base.

[0004] However, since the content stored in the educational knowledge base is content that needs to be used in the teaching process, this method of evaluation has a single dimension and cannot assess the teaching effectiveness, cognitive adaptability, and value orientation of the educational knowledge base in the teaching process, which leads to a disconnect between the evaluation results and the actual teaching effect. Summary of the Invention

[0005] In view of this, this application provides a text quality assessment system for educational databases. The main purpose is to improve the technical problem of existing technologies where the content stored in the educational knowledge base is content that needs to be used in the teaching process. This method has a single assessment dimension and cannot assess the core educational elements such as the teaching effectiveness, cognitive adaptability, and value orientation of the educational knowledge base in the teaching process, thus leading to a disconnect between the assessment results and the actual teaching effect.

[0006] Firstly, this application provides a text quality assessment system for an educational database, comprising: an educational knowledge base, a text quality assessment module, and a fusion analysis module; the text quality assessment module is connected to both the educational knowledge base and the fusion analysis module; the text quality assessment module is used to acquire content feature data corresponding to the content to be assessed in the educational knowledge base, evaluate the content accuracy and teaching adaptability of the content to be assessed from multiple dimensions based on the content feature data, obtain content accuracy data and teaching adaptability data of the content to be assessed, and send the content accuracy data and teaching adaptability data to the fusion analysis module, wherein the content feature data is structured data characterizing the inherent attributes and content quality of the content to be assessed; the fusion analysis module is used to perform fusion analysis on the content accuracy data and the teaching adaptability data according to the content type information corresponding to the content to be assessed, to obtain the quality assessment result of the content to be assessed, wherein the content type information is obtained by functional classification based on the teaching purpose, teaching form, and usage scenario of the content to be assessed.

[0007] Optionally, the text quality assessment module includes: a content accuracy assessment module; the content accuracy assessment module is connected to the educational knowledge base and the fusion analysis module respectively; the content accuracy assessment module is used to identify the set of knowledge points to be assessed corresponding to the content to be assessed from the content feature data; match the set of knowledge points to be assessed with a standard knowledge graph to perform consistency matching of at least one of the content information, question information, analysis information and example information of the knowledge points in the set of knowledge points to be assessed with the standard knowledge information indicated by the standard knowledge graph, to obtain the content accuracy data, and send the content accuracy data to the fusion analysis module.

[0008] Optionally, the text quality assessment module includes: a teaching adaptability assessment module; the teaching adaptability assessment module is connected to the educational knowledge base and the fusion analysis module respectively; the teaching adaptability assessment module is used to evaluate the teaching adaptability of the content to be assessed from multiple dimensions based on the content feature data, obtain the teaching adaptability data corresponding to the content to be assessed, and send the teaching adaptability data to the fusion analysis module, wherein the teaching adaptability data includes teaching effectiveness data, grade level adaptability data, and value score data.

[0009] Optionally, the teaching adaptability assessment module includes: a teaching effectiveness assessment module; the teaching effectiveness assessment module is used to identify teaching element information in the content to be assessed based on the content feature data, generate logical coherence data corresponding to the content to be assessed based on the teaching element information; determine the sentence length information, terminology density information, and logical connector quantity information of the content to be assessed based on the content feature data; assess the ease with which students learn the content to be assessed based on the length information, density information, and quantity information, and obtain the cognitive load coefficient corresponding to the content to be assessed; and generate teaching effectiveness data in the teaching adaptability data based on the logical coherence data and the cognitive load coefficient.

[0010] Optionally, the teaching adaptability assessment module includes: a learning stage adaptability assessment module; the learning stage adaptability assessment module is used to determine the standard language content of the target learning stage corresponding to the content to be assessed, and to evaluate the language style similarity based on the standard language content of the target learning stage and the content to be assessed, so as to obtain the learning stage adaptability data in the teaching adaptability data.

[0011] Optionally, the teaching adaptability assessment module includes a value assessment module; the value assessment module is used to identify key information and sensitive word information in the content to be assessed, and generate value score data in the teaching adaptability data based on the identification results.

[0012] Optionally, the fusion analysis module includes an effectiveness analysis module and a fusion analysis submodule; the effectiveness analysis module is connected to the content accuracy assessment module and the teaching adaptability assessment module respectively, and the fusion analysis submodule is connected to the effectiveness analysis module; the effectiveness analysis module is used to perform effectiveness analysis on the content accuracy data sent by the content accuracy assessment module to obtain content effectiveness data, and send the content effectiveness data to the fusion analysis submodule.

[0013] Optionally, the effectiveness analysis module is used to perform effectiveness analysis on the teaching effectiveness data, the grade level adaptation data, and the value score data sent by the teaching adaptability assessment module to obtain teaching effectiveness data, and then send the teaching effectiveness data to the fusion analysis submodule.

[0014] Optionally, the fusion analysis submodule is used to generate weighted data corresponding to the content accuracy data, teaching effectiveness data, grade level suitability data, and value score data respectively, based on the content effectiveness data and teaching effectiveness data sent by the effectiveness analysis module; and to perform fusion analysis on the content accuracy data, teaching effectiveness data, grade level suitability data, and value score data based on the weighted data to obtain the quality assessment result of the content to be evaluated.

[0015] Secondly, this application provides an electronic device including a text quality assessment system for the educational database described in the first aspect.

[0016] Using the above technical solution, this application provides a text quality assessment system for an educational database, comprising: an educational knowledge base, a text quality assessment module, and a fusion analysis module; the text quality assessment module is connected to both the educational knowledge base and the fusion analysis module; the text quality assessment module is used to acquire content feature data corresponding to the content to be assessed in the educational knowledge base, evaluate the accuracy and teaching adaptability of the content to be assessed from multiple dimensions based on the content feature data, obtain the content accuracy data and teaching adaptability data of the content to be assessed, and send the content accuracy data and teaching adaptability data to the fusion analysis module, wherein the content feature data is structured data representing the inherent attributes and content quality of the content to be assessed; the fusion analysis module is used to perform fusion analysis on the content accuracy data and teaching adaptability data according to the content type information corresponding to the content to be assessed, to obtain the quality assessment result of the content to be assessed, wherein the content type information is obtained by functional classification according to the teaching purpose, teaching form, and usage scenario of the content to be assessed. Compared with existing technologies, this application obtains content feature data of the content to be evaluated in the educational knowledge base through a text quality assessment module, evaluates the accuracy and teaching adaptability of the content from multiple dimensions, obtains content accuracy data and teaching adaptability data, and then performs fusion analysis based on content type information through a fusion analysis module to achieve multi-dimensional evaluation of the content of the educational knowledge base. This makes the evaluation results more consistent with the actual teaching situation, improves the fit between the evaluation results and the actual teaching effect, and enhances the overall teaching effectiveness. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings: Figure 1 shows a schematic structural diagram of a text quality assessment system for an educational database provided in an embodiment of this application; Figure 2 shows a flowchart of an example provided in an embodiment of this application; Figure 3 shows a schematic structural diagram of an electronic device provided in an embodiment of this application.

[0018] In Figure 1: 1-Educational knowledge base; 2-Text quality assessment module; 21-Content accuracy assessment module; 22-Teaching adaptability assessment module; 221-Teaching effectiveness assessment module; 222-School stage adaptability assessment module; 223-Value assessment module; 3-Integration analysis module; 31-Effectiveness analysis module; 32-Integration analysis sub-module. Detailed Implementation

[0019] In the description of this disclosure, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0020] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise expressly specified.

[0021] In this disclosure, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this disclosure according to the specific circumstances.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0023] The following describes, with reference to FIG1, a text quality assessment system for an educational database according to some embodiments of the present disclosure.

[0024] This disclosure provides a text quality assessment system for an educational database, as shown in Figure 1. It includes an educational knowledge base 1, a text quality assessment module 2, and a fusion analysis module 3. The text quality assessment module 2 is connected to both the educational knowledge base 1 and the fusion analysis module 3. The text quality assessment module 2 acquires content feature data corresponding to the content to be assessed in the educational knowledge base 1. Based on the content feature data, it evaluates the accuracy and teaching adaptability of the content to be assessed from multiple dimensions, obtaining content accuracy data and teaching adaptability data. This content accuracy data and teaching adaptability data are then sent to the fusion analysis module 3. The content feature data is structured data representing the inherent attributes and content quality of the content to be assessed. The fusion analysis module 3 performs fusion analysis on the content accuracy data and teaching adaptability data based on the content type information corresponding to the content to be assessed, obtaining the quality assessment result of the content to be assessed. The content type information is obtained by functionally classifying the content according to its teaching purpose, teaching form, and usage scenario.

[0025] In this embodiment of the application, the Educational Knowledge Base 1 is a structured, computable, and scalable collection of knowledge in the field of education. It systematically organizes information such as subject knowledge, teaching methods, learning theories, curriculum standards, typical problems, problem-solving strategies, and student cognitive models, providing reliable, accurate, and reasonable knowledge support for intelligent education systems (such as adaptive learning platforms, AI teaching assistants, automatic question generation systems, and large-scale education models).

[0026] In some examples, the content to be evaluated in the embodiments of this application can be the content in the educational knowledge base 1 that needs to be quality evaluated; for example, the content to be evaluated can include, but is not limited to, text content, such as lesson plans, courseware, documents, and question explanations; video content, such as teaching micro-lessons and live recordings; and interactive content, such as exercises, quizzes, interactive simulations, etc.

[0027] As an optional approach, if new content 1 is added to Educational Knowledge Base 1, then content 1 can be any content in Educational Knowledge Base 1 that requires quality assessment; if content 2 is modified in Educational Knowledge Base 1, then content 2 can also be any content in Educational Knowledge Base 1 that requires quality assessment; if content 3 in Educational Knowledge Base 1 has not undergone quality analysis for a certain period of time, then content 3 can also be any content in Educational Knowledge Base 1 that requires quality assessment, and so on. Examples will not be provided here.

[0028] In this embodiment, content feature data can be quantitative or structured data extracted from the content to be evaluated, which can characterize its inherent attributes and quality dimensions. For example, for text content, content feature data may include, but is not limited to, keyword density, sentence complexity, and the number of logical connectors; for video content, content feature data may include, but is not limited to, the semantic features after speech recognition and text conversion, the clarity of the PPT slides, and the richness of the teacher's body language; for interactive content, content feature data may include, but is not limited to, the question type structure of exercises and their relevance to teaching objectives.

[0029] In this embodiment of the application, the accuracy of the content can be the level of accuracy of the content in terms of scientific validity and factual correctness. The evaluation of the accuracy of the content in this embodiment of the application can not only focus on the surface correctness of the knowledge points, but also include the degree of consistency with standards, such as whether it conforms to the definitions of curriculum standards and textbooks; it can also include the timeliness of the information, such as whether it contains outdated or updated knowledge; and it can also include the degree of consistency with multiple modalities, such as whether there are logical or factual conflicts in different forms such as text, video, and exercises for the same knowledge point.

[0030] In some examples, instructional fit can be considered as the overall effectiveness of the content to be assessed in promoting learning and achieving instructional goals. In this case, the assessment of instructional fit can be comprehensively evaluated from aspects such as the effectiveness of instruction, the degree of adaptation of students' cognition, and the correctness of values ​​and safety.

[0031] In this embodiment, the text quality assessment module 2 receives content feature data corresponding to the content to be assessed sent by the educational knowledge base 1. The content feature data is structured data extracted by the educational knowledge base 1 based on the inherent attributes and content quality of the content to be assessed. After the text quality assessment module 2 completes the calculation of the content accuracy data and teaching adaptability data, it directly sends the content accuracy data and teaching adaptability data to the fusion analysis module 3. The fusion analysis module 3 receives the content accuracy data and teaching adaptability data and temporarily stores them.

[0032] As an alternative approach, if new content 1 is added to the educational knowledge base 1, then content 1 can be content in the educational knowledge base 1 that needs to be evaluated for quality. In this case, the content feature data 1 corresponding to content 1 can be determined, and then the accuracy and teaching adaptability of content 1 can be evaluated based on the content feature data 1 to obtain the content accuracy data 1 and teaching adaptability data 1 corresponding to content 1.

[0033] As an alternative approach, if content 2 is modified in educational knowledge base 1, then content 2 can also be content in educational knowledge base 1 that needs to be evaluated for quality. In this case, the content feature data 2 corresponding to content 2 can be determined, and then the accuracy and teaching suitability of content 2 can be evaluated based on the content feature data 2 to obtain the content accuracy data 2 and teaching suitability data 2 corresponding to content 2.

[0034] As an alternative approach, if content 3 in educational knowledge base 1 has not undergone quality analysis for a certain period of time, then content 3 can also be content in educational knowledge base 1 that needs to be quality assessed. In this case, the content feature data 3 corresponding to content 3 can be determined, and then the accuracy and teaching adaptability of content 3 can be assessed based on the content feature data 3 to obtain the content accuracy data 3 and teaching adaptability data 3 corresponding to content 3.

[0035] In this embodiment, the content type information can be the content type information of the content to be evaluated. Specifically, the content type information can be obtained by functionally classifying the content to be evaluated based on its teaching purpose, form, and usage scenario. For example, the content type information may include, but is not limited to, popular science video type, legal provision type, teaching micro-lesson type, exercise solution type, etc.

[0036] In some examples, the quality assessment result can be the result of a quality assessment of the content to be assessed. Specifically, the quality assessment can take various forms, including but not limited to a comprehensive quality score multi-dimensional quality profile, a visual representation (such as a radar chart), etc.

[0037] As an alternative approach, if new content 1 is added to the educational knowledge base 1, then content 1 can be content in the educational knowledge base 1 that needs to be quality assessed. In this case, the content feature data 1 corresponding to content 1 can be determined, and then the accuracy and teaching suitability of content 1 can be assessed based on the content feature data 1 to obtain the content accuracy data 1 and teaching suitability data 1 corresponding to content 1. Then, the content accuracy data 1 and teaching suitability data 1 can be fused and analyzed based on the content type information 1 to obtain the quality assessment result 1 of content 1.

[0038] As an alternative approach, if content 2 is modified in educational knowledge base 1, then content 2 can also be content in educational knowledge base 1 that needs to be quality assessed. In this case, the content feature data 2 corresponding to content 2 can be determined, and then the accuracy and teaching adaptability of content 2 can be assessed based on the content feature data 2 to obtain the content accuracy data 2 and teaching adaptability data 2 corresponding to content 2. Then, the content accuracy data 2 and teaching adaptability data 2 can be fused and analyzed according to the content type information 2 to obtain the quality assessment result 2 of content 2.

[0039] As an alternative approach, if content 3 in educational knowledge base 1 has not undergone quality analysis for a certain period of time, then content 3 can also be considered content in educational knowledge base 1 that requires quality assessment. In this case, the content feature data 3 corresponding to content 3 can be determined, and then the accuracy and teaching suitability of content 3 can be assessed based on the content feature data 3, resulting in the content accuracy data 3 and teaching suitability data 3 corresponding to content 3. Furthermore, the content accuracy data 3 and teaching suitability data 3 can be integrated and analyzed based on the content type information 3 to obtain the quality assessment result 3 of content 3.

[0040] Compared with existing technologies, this embodiment obtains content feature data of the content to be evaluated in the educational knowledge base through a text quality assessment module, evaluates the accuracy and teaching adaptability of the content from multiple dimensions, obtains content accuracy data and teaching adaptability data, and then performs fusion analysis based on content type information through a fusion analysis module to achieve multi-dimensional evaluation of the content of the educational knowledge base. This makes the evaluation results more consistent with the actual teaching situation, improves the fit between the evaluation results and the actual teaching effect, and enhances the overall teaching effectiveness.

[0041] Optionally, the text quality assessment module 2 includes: a content accuracy assessment module 21; the content accuracy assessment module 21 is connected to the educational knowledge base 1 and the fusion analysis module 3 respectively; the content accuracy assessment module 21 is used to identify the set of knowledge points to be assessed corresponding to the content to be assessed from the content feature data; the set of knowledge points to be assessed is matched with the standard knowledge graph to ensure consistency matching of at least one of the content information, question information, analysis information and example information of the knowledge points in the set of knowledge points to be assessed with the standard knowledge information indicated by the standard knowledge graph, to obtain content accuracy data, and the content accuracy data is sent to the fusion analysis module 3.

[0042] In this embodiment of the application, the set of knowledge points to be evaluated can be a set of knowledge points that constitute the core teaching theme and are automatically identified and extracted from the content to be evaluated (such as lesson plans, videos, and exercises).

[0043] For example, if the content to be evaluated is a teaching video of "Newton's First Law", then knowledge points such as "inertia" and "relationship between force and motion" can be extracted from the teaching video of "Newton's First Law" to form the set of knowledge points to be evaluated in this application embodiment.

[0044] It should be noted that the set of knowledge points to be evaluated in this application embodiment can exist in various forms such as text description, chart, formula or interactive demonstration. The specific form of the set of knowledge points to be evaluated is not specifically limited in this application embodiment.

[0045] In this embodiment, the standard knowledge graph can be a structured knowledge graph validated in the education field. The standard knowledge graph in this embodiment can be used to match various information of the set of knowledge points to be evaluated, thereby obtaining the accuracy data of the content to be evaluated.

[0046] In some examples, embodiments of this application can logically, semantically, and factually match the content information (such as definitions and descriptions), question information (such as exercise stems), analytical information (such as problem-solving steps), and example information (such as teaching cases) of the knowledge points in the set of knowledge points to be evaluated with the corresponding standard knowledge information in the standard knowledge graph. In the matching process, it is necessary not only to check literal consistency, but also to identify potential conceptual biases, ambiguities in expression, logical jumps, or factual errors through the deep reasoning capabilities of the Large Language Model (LLM).

[0047] For example, embodiments of this application can compare the content information, question information, analysis information, and example information of the knowledge points in the set of knowledge points to be evaluated with educational knowledge graphs (such as curriculum standards, textbooks, encyclopedias, etc.) and use the reasoning ability of LLM to identify potential factual contradictions or outdated information.

[0048] In this embodiment of the application, the content accuracy assessment module 21 receives the content feature data corresponding to the content to be assessed sent by the educational knowledge base 1, and accurately identifies the set of knowledge points to be assessed corresponding to the content to be assessed from the content feature data; the content accuracy assessment module 21 sends the identified set of knowledge points to be assessed to the standard knowledge graph system, and receives the standard knowledge information corresponding to the set of knowledge points to be assessed returned by the standard knowledge graph system; after obtaining the content accuracy data through consistency matching, the content accuracy assessment module 21 sends the content accuracy data to the fusion analysis module 3, and the fusion analysis module 3 receives and stores the content accuracy data.

[0049] As an optional approach, if the knowledge point in the set of knowledge points to be evaluated is "Newton's First Law", then LLM can be used to determine whether the content description is consistent with the curriculum standard definition, check whether the examples given (such as "driving cars") are appropriate, and check whether there are information conflicts between the text explanation, accompanying video, and related exercises for the same knowledge point. For example, if the formula explained in the video is F=ma, but the answer to the accompanying exercise incorrectly uses F=mv, then an inconsistency alarm will be triggered, so that the embodiments of this application can ensure that the knowledge content is scientific and accurate.

[0050] Optionally, the text quality assessment module 2 includes: a teaching adaptability assessment module 22; the teaching adaptability assessment module 22 is connected to the educational knowledge base 1 and the fusion analysis module 3 respectively; the teaching adaptability assessment module 22 is used to evaluate the teaching adaptability of the content to be assessed from multiple dimensions based on content feature data, obtain the teaching adaptability data corresponding to the content to be assessed, and send the teaching adaptability data to the fusion analysis module 3, wherein the teaching adaptability data includes teaching effectiveness data, grade level adaptability data, and value score data.

[0051] In this embodiment of the application, teaching effectiveness data can be a quantitative indicator for measuring the quality of instructional design and the clarity of explanation of the content to be evaluated. It can comprehensively evaluate whether the content is easy for students to understand and master, and whether effective teaching strategies (such as setting guiding questions, providing typical examples, and conducting concept clarification) are used.

[0052] As an alternative approach, embodiments of this application may use an LLM fine-tuned with an educational theory corpus to identify whether the content contains elements of classic teaching methods, such as: advance organizers (introductory materials before introducing new concepts), exemplification (whether the examples are typical and abundant), concept clarification (whether easily confused points are clearly distinguished), etc., thereby determining the logical coherence data of the content to be evaluated.

[0053] It should be noted that, in this embodiment, teaching element information in the content to be evaluated is identified based on content feature data, and logical coherence data corresponding to the content to be evaluated is generated based on the teaching element information; the length information of sentences, the density information of professional terms, and the number of logical connectors in the content to be evaluated are determined based on the content feature data; the ease of students learning the content to be evaluated is assessed based on the length information, density information, and number information, and the cognitive load coefficient corresponding to the content to be evaluated is obtained; based on the logical coherence data and the cognitive load coefficient, teaching effectiveness data in the teaching adaptability data is generated, which can assess whether the content to be evaluated has good instructional design and dissemination effect, and is easy for students to understand and master.

[0054] In this embodiment of the application, the teaching adaptability assessment module 22 receives the content feature data corresponding to the content to be assessed sent by the educational knowledge base 1, and conducts multi-dimensional evaluation based on the content feature data; after the teaching adaptability data (including teaching effectiveness data, grade level adaptability data and value score data) is generated, the teaching adaptability assessment module 22 sends the teaching adaptability data to the fusion analysis module 3, and the fusion analysis module 3 receives the teaching adaptability data and associates it with the content accuracy data with the same content identifier.

[0055] Optionally, the teaching adaptability assessment module 22 includes: a teaching effectiveness assessment module 221; the teaching effectiveness assessment module 221 uses content feature data to identify teaching element information in the content to be assessed, and generates logical coherence data corresponding to the content to be assessed based on the teaching element information; it determines the sentence length information, terminology density information, and number of logical connectors in the content to be assessed based on the content feature data; it assesses the ease with which students learn the content to be assessed based on the length information, density information, and number information, and obtains the cognitive load coefficient corresponding to the content to be assessed; and it generates teaching effectiveness data in the teaching adaptability data based on the logical coherence data and the cognitive load coefficient.

[0056] In some examples, instructional element information can be structured instructional design components identified from the content to be assessed to achieve the instructional objectives. These may include, but are not limited to, introductory background materials or analogies provided before introducing a new concept, typical and specific examples used to explain a concept or method, clear distinctions and comparisons of easily confused concepts, and other identifiable instructional strategy elements such as summaries and reviews, interactive question designs, etc.

[0057] In this embodiment, logical coherence data can be an indicator for quantitatively assessing whether the internal logical structure of the content to be assessed is clear, orderly, and self-consistent. Specifically, logical coherence data can be a score value generated by a large language model (LLM) or related algorithm model that has been fine-tuned by educational corpus, through analysis of the organizational structure, order of discussion, and semantic connection of teaching element information.

[0058] In some examples, sentence length information can be the average length of sentences or the proportion of long sentences in the content to be assessed. Sentences that are too long may indicate high information density or complex structure, which may increase the burden on students' comprehension. Correspondingly, terminology density information can be the frequency of occurrence of domain-specific professional terms or concepts in the content to be assessed. Excessive terminology density may exceed the students' prior knowledge, leading to an increased cognitive load on students.

[0059] In this embodiment, the quantity information of logical connectors can be the number or proportion of connectors or phrases used to express logical relationships such as cause and effect, contrast, parallelism, and progression in the content to be evaluated (e.g., "because...therefore...", "however", "on the other hand", etc.).

[0060] In some examples, the cognitive load coefficient can be used to characterize the level of mental effort required for students to learn and understand the content. In the embodiments of this application, the cognitive load coefficient can be calculated based on the analysis of the length of the sentence, the density of technical terms, the number of logical connectors, and the conceptual complexity and structure of the content itself. The higher the cognitive load coefficient, the greater the cognitive load on the student for the content to be evaluated, and the more difficult the content to be evaluated is to understand.

[0061] For example, in this embodiment, a segment of explanatory text from the content to be evaluated can be input into the LLM model. The LLM model calculates the average sentence length, terminology density, and number of logical connectors. Combined with concept dependency graph analysis, the cognitive load coefficient required for student comprehension is assessed, resulting in the cognitive load coefficient in this embodiment. Then, teaching effectiveness data in the teaching fitness data is generated using Formula 1, which is shown below: Clarity Score = LLM - Logical Coherence Score * 0.6 + (1 - Cognitive Load Coefficient) * 0.4 (Formula 1). In this embodiment, the teaching effectiveness assessment module 221 can receive the text to be evaluated forwarded by the teaching fitness assessment module 22. The teaching effectiveness assessment module 221 can determine the length of sentences, the density of professional terms, and the number of logical connectors based on the content feature data. Then, it inputs the length, density, and number information into the cognitive load assessment model and receives the cognitive load coefficient corresponding to the content to be assessed returned by the model. After generating teaching effectiveness data based on the logical coherence data and the cognitive load coefficient, the teaching effectiveness assessment module 221 can send the teaching effectiveness data to the teaching fitness assessment module 22. The teaching fitness assessment module 22 receives the data and incorporates it into the teaching fitness data set.

[0062] Optionally, the teaching adaptability assessment module 22 includes: a grade level adaptability assessment module 222; the grade level adaptability assessment module 222 is used to determine the standard language content of the target grade level corresponding to the content to be assessed, and to evaluate the language style similarity based on the standard language content of the target grade level and the content to be assessed, so as to obtain the grade level adaptability data in the teaching adaptability data.

[0063] In some examples, the standard language content for the target learning stage can be a set of normative and exemplary language materials recognized by the education field for students of a specific grade or educational stage (such as "third grade of primary school" or "second year of junior high school"). This set can be used to characterize the language complexity, sentence structure and expression style characteristics that learners of that age are suitable to encounter.

[0064] For example, language style similarity evaluation can be achieved by using a computational model or algorithm to quantitatively compare the consistency or closeness of the content to be evaluated with the standard language content of the target learning level in terms of language features. Evaluation dimensions may include, but are not limited to: lexical complexity, such as vocabulary difficulty level, proportion of uncommon words, etc.; syntactic structure, such as average sentence length, frequency of clause usage, sentence diversity, etc.; and expression habits, such as rhetorical devices, formality of tone, etc. In the embodiments of this application, the evaluation result of language style similarity evaluation may be a quantitative similarity score, but it is not limited to this, and will not be listed in detail here.

[0065] In this embodiment, the stage-appropriateness data can be a quantitative indicator generated based on the language style similarity evaluation results. The stage-appropriateness data in this embodiment reflects the degree of matching between the content to be evaluated and the cognitive development stage of the target learners in terms of language difficulty and expression. The stage-appropriateness data in this embodiment can also be comprehensively corrected by combining the LLM judgment on the suitability of the case background (for example, judging whether the use of the "online game" case is appropriate for primary school students).

[0066] In this embodiment of the application, the grade level adaptation assessment module 222 can receive the content to be assessed and the corresponding target grade level information sent by the teaching adaptation assessment module 22, send a request to the standard language content database, and receive the standard language content corresponding to the target grade level returned by the database; the grade level adaptation assessment module 222 can compare the standard language content of the target grade level with the content to be assessed, generate grade level adaptation data after completing the language style similarity evaluation, and send the grade level adaptation data to the teaching adaptation assessment module 22, and the teaching adaptation assessment module 22 receives the grade level adaptation data.

[0067] As an optional approach, embodiments of this application can train standard language models for different age groups (i.e., standard language content in embodiments of this application) based on textbooks and excellent reading materials for each grade level. Then, based on the content to be evaluated and the target grade level (e.g., "fifth grade of primary school"), the similarity of language style (e.g., lexical complexity, syntactic structure) between the content to be evaluated and the corresponding grade level benchmark model (i.e., standard language content in embodiments of this application) can be calculated. At the same time, LLM can also be used to determine the age-appropriateness of the case background (e.g., whether using "online games" as a case is appropriate for primary school students).

[0068] It should be noted that, in this embodiment of the application, by determining the standard language content of the target learning stage corresponding to the content to be evaluated, and by evaluating the language style similarity based on the standard language content of the target learning stage and the content to be evaluated, the learning stage fit data in the teaching adaptability data can be obtained, which can ensure that the language style, case background, cognitive difficulty of the content match the age and cognitive development stage of the target learners.

[0069] Optionally, the teaching adaptability assessment module 22 includes: a value assessment module 223; the value assessment module 223 is used to identify key information and sensitive word information in the content to be assessed, and generate value score data in the teaching adaptability data based on the identification results.

[0070] In some examples, key point information can be expressions or implications of content points that may involve value guidance, ideology, social sensitivity, ethics, etc. in the content to be evaluated. This information may not necessarily be presented through obvious keywords, but may need to be identified through semantic understanding to identify its potential tendencies or influences. Correspondingly, sensitive word information can be specific words, phrases or expression patterns that appear in the content to be evaluated. In the embodiments of this application, key point information and sensitive word information can be identified by combining a preset sensitive word library with contextual semantic analysis.

[0071] In this embodiment, the value score data can be a comprehensive safety and values ​​compliance score. The value score data can be generated based on the identification results of key point information and sensitive word information, and further through a value-aligned fine-tuned Large Language Model (LLM) to conduct in-depth semantic analysis and scoring of the content's theme, tendency, and the value orientation of the case. The higher the value score data score, the more the content meets the students' learning requirements in terms of values ​​and safety.

[0072] As an alternative approach, embodiments of this application can identify sensitive information based on keywords and semantics, and use a value-aligned LLM to score the main idea, tendency, and value orientation of the content and the case, thereby obtaining the value score data in embodiments of this application.

[0073] In this embodiment, the value assessment module 223 can receive the content to be assessed sent by the teaching adaptability assessment module 22, and start the recognition engine to identify key point information and sensitive word information in the content to be assessed; the value assessment module 223 can send the identified key point information and sensitive word information to the value scoring system, and receive the value scoring suggestions returned by the value scoring system based on the recognition results; after generating value scoring data according to the recognition results and value scoring suggestions, the value assessment module 223 can send the value scoring data to the teaching adaptability assessment module 22, and the teaching adaptability assessment module 22 receives the data and integrates it into the teaching adaptability data.

[0074] Optionally, the fusion analysis module 3 includes an effectiveness analysis module 31 and a fusion analysis submodule 32. The effectiveness analysis module 31 is connected to the content accuracy assessment module 21 and the teaching adaptability assessment module 22, respectively, and the fusion analysis submodule 32 is connected to the effectiveness analysis module 31. The effectiveness analysis module 31 is used to perform effectiveness analysis on the content accuracy data sent by the content accuracy assessment module 21, obtain content effectiveness data, and send the content effectiveness data to the fusion analysis submodule 32.

[0075] In this embodiment, the validity data can be a quantitative parameter pre-set based on the content type information for each evaluation dimension (content accuracy, teaching effectiveness, grade level suitability, and value score), reflecting the importance or contribution of that dimension to the content of that type. For example, for "legal provisions," the validity of the "accuracy" dimension is relatively high (e.g., 0.6), while the validity of the "teaching effectiveness" dimension is relatively low (e.g., 0.1).

[0076] In some examples, the weight data can be a coefficient that adjusts the proportion of influence of each dimension score on the final comprehensive quality score when multi-dimensional fusion calculation is performed; in the embodiments of this application, the weight data can be generated based on the effectiveness data and can be dynamically adjusted in the future according to actual teaching feedback. Each dimension (such as accuracy, teaching effectiveness, etc.) corresponds to a weight value, and the sum of all weights is usually 1.

[0077] In this embodiment, the fusion analysis can be a process of weighting and comprehensively calculating the four evaluation results—content accuracy data, teaching effectiveness data, grade level suitability data, and value score data—according to their corresponding weights. In this embodiment, the weighted analysis can generate a single quantitative result or structured evaluation that can comprehensively and balancedly reflect the overall quality level of the content.

[0078] As an optional approach, as shown in Figure 2, the weights in this embodiment can be preset based on the content type. For example, for popular science videos, the weight data can be preset as teaching effectiveness (0.5) > accuracy (0.3) > suitability (0.2); for legal provisions, the weight data can be preset as accuracy (0.6) > security (0.3) > effectiveness (0.1), etc., and so on. No further examples will be given here.

[0079] Optionally, the effectiveness analysis module 31 is used to analyze the effectiveness of the teaching effectiveness data, grade level fit data and value score data sent by the teaching adaptability assessment module 22, obtain the teaching effectiveness data, and send the teaching effectiveness data to the fusion analysis submodule 32.

[0080] In this embodiment, the validity analysis module 31 can receive content accuracy data sent by the content accuracy evaluation module 21. The content accuracy data can be the evaluation data generated by the content accuracy evaluation module 21 through consistency matching. The validity analysis module 31 can perform validity analysis on the content accuracy data, generate content validity data, and then send the content validity data to the fusion analysis submodule 32. The fusion analysis submodule 32 receives and stores the content validity data.

[0081] Optionally, the effectiveness analysis module 31 is used to analyze the effectiveness of the teaching effectiveness data, grade level fit data and value score data sent by the teaching adaptability assessment module 22, obtain the teaching effectiveness data, and send the teaching effectiveness data to the fusion analysis submodule 32.

[0082] In this embodiment, the effectiveness analysis module 31 can receive teaching effectiveness data, grade level fit data, and value score data sent by the teaching adaptability assessment module 22. The teaching effectiveness data, grade level fit data, and value score data can be the core components of the teaching adaptability data integrated and generated by the teaching adaptability assessment module 22. The effectiveness analysis module 31 can perform effectiveness analysis on the teaching effectiveness data, grade level fit data, and value score data respectively, and after integrating them to obtain teaching effectiveness data, send the teaching effectiveness data to the fusion analysis submodule 32. The fusion analysis submodule 32 receives the data and associates it with the content effectiveness data.

[0083] Optionally, the fusion analysis submodule 32 is used to generate weighted data corresponding to content accuracy data, teaching effectiveness data, grade level suitability data, and value score data based on the content effectiveness data and teaching effectiveness data sent by the effectiveness analysis module 31; and to perform fusion analysis on the content accuracy data, teaching effectiveness data, grade level suitability data, and value score data based on the weighted data to obtain the quality assessment result of the content to be evaluated.

[0084] In this embodiment, the weight data can be the specific weight values ​​of each evaluation dimension currently applied to the target teaching content. The weight data can be generated and updated based on content type information and effectiveness data.

[0085] In this embodiment, the actual teaching effect reflected by the teaching feedback data can be compared with the expected effect predicted based on the target effectiveness data (i.e., the weight data in this embodiment). If there is a significant difference (e.g., the content scores high in teaching effectiveness, but the students' actual test accuracy is low), the target weight data of the corresponding dimension can be automatically adjusted up or down to make the evaluation model more in line with the real teaching scenario and realize the self-calibration and continuous optimization of the evaluation standard.

[0086] For example, in this application embodiment, if the content to be evaluated scores high in teaching effectiveness, but the corresponding student's post-learning test accuracy rate remains low, the weight of the teaching effectiveness dimension can be automatically increased, and a second review of the content can be triggered through Formula 2, which is shown below: W_i(t+1)=W_i(t)+ *(Learning performance index - Predicted performance index) (Formula 2) In Formula 2, W_i represents the weight of the i-th dimension.

[0087] For example, embodiments of this application can also generate quality assessment results for the content to be evaluated using Formula 3, and then output a visual radar chart to intuitively display the strengths and weaknesses of the content in various dimensions. Formula 3 is as follows: Final quality score Q = (Dimensional Score_i * Dynamic Weight_W_i) (Formula 3) In this embodiment, the fusion analysis submodule 32 receives content effectiveness data and teaching effectiveness data sent by the effectiveness analysis module 31. Based on the content effectiveness data and teaching effectiveness data, it can generate weight data corresponding to content accuracy data, teaching effectiveness data, grade level suitability data, and value score data respectively through a preset algorithm. The fusion analysis submodule 32 can send raw data query requests to the content accuracy assessment module 21 and the teaching suitability assessment module 22, and receive the returned content accuracy data, teaching effectiveness data, grade level suitability data, and value score data. After completing the fusion analysis based on the weight data, the fusion analysis submodule 32 can generate the quality assessment result of the content to be evaluated, and send the quality assessment result to the system result output module or store it in a specified database.

[0088] Implementation Case: Quality Inspection of Elementary School Mathematics Knowledge Base of an Online Education Platform.

[0089] As an optional approach, this application embodiment may also provide the following examples, but not limited to these, including: Adding 5000 primary school mathematics teaching videos and accompanying exercises to the educational knowledge base 1, the videos can be converted into text via ASR and input into the evaluation engine along with the exercise text. In the evaluation engine, the model detects that when a video explains "long division," the step description deviates slightly from authoritative textbooks, resulting in an accuracy score of 0.7. Another video, explaining the "chicken and rabbit in the same cage" problem, uses vivid animation and gradual guidance, which is recognized by LLM as employing a good "problem decomposition" strategy, resulting in an effectiveness score of 0.9. A certain exercise solution uses the concept of "two linear equations in two variables," but the target label is "fourth grade primary school," and the system judges this content to be beyond the curriculum, resulting in an suitability score of only 0.4. One week later, data shows that the student completion rate and the accuracy rate of the after-class exercises for the "chicken and rabbit in the same cage" video are both very high, verifying the effectiveness of the evaluation, and its overall quality score is dynamically improved. The video on "vertical division" with a deviation had an unusually high number of student questions, triggering a high-priority re-review alert. The system generated a quality report, marking high-quality content for recommendation and listing content that needed optimization or removal, along with specific reasons (such as "concepts beyond the syllabus" or "ambiguous explanations"). Based on the report, targeted optimizations were made, resulting in a 30% increase in the teacher and student approval rating for that module's knowledge base.

[0090] It should be noted that the embodiments of this application can use massive amounts of corpora such as lesson plans, curriculum standards, excellent papers, and educational monographs to continue pre-training and fine-tuning the base LLM, giving it "professional intuition" in the field of education; for video content, its visual information (PPT clarity, teacher body language) and semantic information from speech-to-text are fused and analyzed to jointly evaluate the effectiveness of teaching; and based on the reinforcement learning approach, the contribution of each quality dimension can be automatically optimized according to the "evaluation-feedback" closed loop, making the system more and more "intelligent" the more it is used.

[0091] It should be noted that the embodiments of this application propose an "educational adaptability" quality model, breaking through the traditional assessment paradigm centered on "accuracy," and constructing a comprehensive assessment system covering four core educational dimensions: accuracy, effectiveness, adaptability, and safety, achieving a leap from "information correctness" to "teaching effectiveness"; a dynamic feedback-driven weight adjustment mechanism is introduced. The static AI assessment results are correlated with real teaching effectiveness data (learning outcomes), and the assessment standards are self-calibrated through a dynamic weight algorithm, making the assessment results more practically instructive; LLM (Learning Learning Model) with enhanced knowledge in the education field is applied. Through fine-tuning with a large-scale educational corpus, LLM can, like an experienced teacher, deeply understand the strengths and weaknesses of instructional design and the age-appropriateness of cases, solving the problem of "unprofessionalism" of general models in the education field.

[0092] In related technologies, many rely on superficial indicators such as keyword density and text readability, failing to assess core educational elements such as teaching effectiveness (e.g., clarity of concept explanation), cognitive suitability (e.g., whether it conforms to the cognitive patterns of students at a specific age group), and value orientation. Existing tools are mostly one-time static assessments, unable to dynamically optimize and iterate based on the content's effectiveness in actual teaching scenarios (e.g., student answer accuracy, interaction activity, teacher evaluation), leading to a disconnect between assessment results and actual teaching outcomes. The educational knowledge base 1 contains multimodal content such as videos, audio, and interactive exercises. Traditional methods struggle to uniformly assess the logic of video explanations and the matching degree between exercises and teaching objectives, resulting in blind spots in assessment. Manual review is time-consuming, costly, and inconsistent in standards, making it difficult to cope with massive UGC (user-generated content) and rapidly updated online educational content libraries, becoming a bottleneck for quality control.

[0093] It should be noted that the embodiments of this application achieve a unified assessment of the scientific and educational nature of educational knowledge content, with an assessment dimension coverage rate of over 95%. Compared with purely manual review, the assessment efficiency is improved by more than 50 times, and it can handle the addition and updates of tens of thousands of pieces of content every day. Through a dynamic weighting mechanism, it ensures that high-quality content (i.e., content that students can truly understand and learn) is accurately identified and recommended, thereby improving the overall teaching effectiveness of the knowledge base. It can also achieve automated value and security screening, reducing the missed detection rate of potentially risky content to below 1%.

[0094] Compared with existing technologies, this embodiment improves the accuracy of content accuracy assessment by identifying the set of knowledge points to be assessed and matching them with a standard knowledge graph through a content accuracy assessment module, verifying the consistency of knowledge point information, and improving the accuracy of content accuracy assessment; by using a teaching adaptability assessment module to evaluate the degree of teaching adaptability from multiple dimensions based on content feature data, generating data including teaching effectiveness, grade level suitability, and value score, achieving a comprehensive assessment of core educational elements; by using a teaching effectiveness assessment module to identify teaching elements, determine relevant information of sentences, and assess cognitive load coefficients, generating teaching effectiveness data, and improving the relevance of teaching effectiveness assessment; and by using a grade level suitability assessment module to evaluate language style similarity based on standard language content for the target grade level. The system obtains data on the suitability of content for different learning stages, enabling an assessment of the cognitive fit between the content and the target learning stage. The value assessment module identifies key points and sensitive words to generate value score data, achieving effective evaluation of value orientation. The effectiveness analysis module analyzes content accuracy data to obtain content effectiveness data, providing a reliable foundation for integrated analysis. The effectiveness analysis module further analyzes the effectiveness of teaching effectiveness data, learning stage suitability data, and value score data to obtain teaching effectiveness data, improving the data source support for integrated analysis. Finally, the integrated analysis submodule generates weighted data and integrates various assessment data to obtain accurate quality assessment results, reducing the risk of discrepancies between the results and actual teaching effectiveness.

[0095] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0096] Figure 3 shows a schematic diagram of the hardware structure of an electronic device according to the present invention, including: at least one processor 201; and a memory 202 communicatively connected to at least one processor 201; wherein, the memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to perform the control method of the protection device as described above.

[0097] Figure 3 uses a processor 201 as an example.

[0098] The electronic device may also include an input device 203 and a display device 204.

[0099] The processor 201, memory 202, input device 203 and display device 204 can be connected by a bus or other means. Figure 3 shows an example of connection by bus.

[0100] The memory 202, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the control method of the protection device in the embodiments of this application, for example, the method flow shown in Figures 1 and 2. The processor 201 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 202, thereby implementing the control method of the protection device in the above embodiments.

[0101] The memory 202 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the control method of the protection device. Furthermore, the memory 202 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 202 may optionally include memory remotely located relative to the processor 201, and these remote memories may be connected via a network to the means of performing the control method of the protection device. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0102] The input device 203 can receive user clicks and generate signal inputs related to user settings and function control of the protection device's control method. The display device 204 may include a display screen or other display equipment.

[0103] One or more modules are stored in memory 202, and when run by one or more processors 201, they execute the control method of the protection device in any of the above method embodiments.

[0104] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0105] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0106] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0107] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. By applying the solution of this embodiment, compared with the existing technology, this embodiment obtains the content feature data of the content to be evaluated in the educational knowledge base through the text quality assessment module, evaluates the accuracy and teaching adaptability of the content from multiple dimensions, obtains content accuracy data and teaching adaptability data, and then performs fusion analysis based on content type information through the fusion analysis module to realize multi-dimensional evaluation of the content of the educational knowledge base, making the evaluation results more consistent with the real teaching situation, improving the fit between the evaluation results and the actual teaching effect, and improving the overall teaching effectiveness; the content accuracy assessment module identifies the set of knowledge points to be evaluated and matches them with the standard knowledge graph to verify the consistency of knowledge point information and improve the accuracy of content accuracy assessment; the teaching adaptability assessment module evaluates the teaching adaptability based on the content feature data from multiple dimensions, generates data including teaching effectiveness, grade level adaptability, and value score, and realizes a comprehensive evaluation of the core elements of education; the teaching effectiveness assessment module evaluates the teaching adaptability based on the content feature data from multiple dimensions, generates data including teaching effectiveness, grade level adaptability, and value score, and realizes a comprehensive evaluation of the core elements of education; the teaching effectiveness assessment module evaluates the teaching adaptability based on the teaching feature data from multiple dimensions, generates data including teaching effectiveness, grade level adaptability, and value score, and realizes a comprehensive evaluation of the core elements of education; the teaching effectiveness assessment module evaluates the teaching adaptability based on the teaching feature data. The assessment module identifies teaching elements, determines relevant information about sentences, and evaluates cognitive load coefficients to generate teaching effectiveness data, thereby improving the relevance of teaching effectiveness assessment. The grade-level fit assessment module evaluates language style similarity based on standard language content for the target grade level, obtaining grade-level fit data to achieve cognitive fit assessment between content and the target grade level. The value assessment module identifies key points and sensitive word information, generating value score data to achieve effective value-oriented assessment. The effectiveness analysis module analyzes content accuracy data to obtain content effectiveness data, providing a reliable foundation for integrated analysis. The effectiveness analysis module also analyzes the effectiveness of teaching effectiveness data, grade-level fit data, and value score data to obtain teaching effectiveness data, improving the data source support for integrated analysis. Finally, the integrated analysis submodule generates weighted data and integrates various assessment data to obtain accurate quality assessment results, reducing the risk of disconnection from actual teaching effectiveness.

[0108] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0109] The above are merely specific embodiments of this disclosure, enabling those skilled in the art to understand or implement this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0110] It should be noted that the technical solutions in this disclosure are not limited to use in the control circuit of protection devices, but can also be extended to related applications of the same type that require control. All of these should fall within the protection scope of this disclosure, and no specific limitations are made here for the related applications that require control.

[0111] All articles and references disclosed above, including patent applications and publications, are incorporated herein by reference for various purposes. The term “substantially constitutes…” used to describe a combination should include the identified elements, components, parts, or steps, as well as other elements, components, parts, or steps that do not substantially affect the essential novelty of the combination. The use of the terms “comprising” or “including” to describe combinations of elements, components, parts, or steps herein also contemplates embodiments substantially constituted by such elements, components, parts, or steps. The use of the term “may” herein is intended to indicate that any described attribute included by “may” is optional.

[0112] Multiple elements, components, parts, or steps can be provided by a single integrated element, component, part, or step. Alternatively, a single integrated element, component, part, or step can be divided into multiple separate elements, components, parts, or steps. The use of "a" or "an" to describe an element, component, part, or step does not imply the exclusion of other elements, components, parts, or steps.

[0113] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this teaching should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and published disclosures, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be considered as a failure of the applicant to consider that subject matter as part of the disclosed subject matter. It will be apparent to those skilled in the art that various modifications and variations can be made to this disclosure without departing from its spirit and scope. Thus, this disclosure is also intended to include such modifications and variations if they fall within the scope of the claims of this disclosure and their equivalents.

Claims

1. A text quality assessment system for an educational database, characterized in that, include: The system comprises an educational knowledge base, a text quality assessment module, and a fusion analysis module. The text quality assessment module is connected to both the educational knowledge base and the fusion analysis module. The text quality assessment module acquires content feature data corresponding to the content to be assessed from the educational knowledge base. Based on the content feature data, it evaluates the accuracy and teaching adaptability of the content to be assessed from multiple dimensions, obtaining content accuracy data and teaching adaptability data. This content accuracy data and teaching adaptability data are then sent to the fusion analysis module. The content feature data is structured data characterizing the inherent attributes and content quality of the content to be assessed. The fusion analysis module performs fusion analysis on the content accuracy data and teaching adaptability data based on the content type information corresponding to the content to be assessed, obtaining a quality assessment result for the content to be assessed. The content type information is obtained through functional classification based on the teaching objectives, teaching methods, and usage scenarios of the content to be assessed.

2. The system according to claim 1, characterized in that, The text quality assessment module includes: a content accuracy assessment module; the content accuracy assessment module is connected to the educational knowledge base and the fusion analysis module respectively; the content accuracy assessment module is used to identify the set of knowledge points to be assessed corresponding to the content to be assessed from the content feature data; match the set of knowledge points to be assessed with a standard knowledge graph, so as to perform consistency matching between at least one of the content information, question information, analysis information and example information of the knowledge points in the set of knowledge points to be assessed and the standard knowledge information indicated by the standard knowledge graph, to obtain the content accuracy data, and send the content accuracy data to the fusion analysis module.

3. The system according to claim 1, characterized in that, The text quality assessment module includes a teaching adaptability assessment module; the teaching adaptability assessment module is connected to the educational knowledge base and the fusion analysis module respectively; the teaching adaptability assessment module is used to evaluate the teaching adaptability of the content to be assessed from multiple dimensions based on the content feature data, obtain the teaching adaptability data corresponding to the content to be assessed, and send the teaching adaptability data to the fusion analysis module, wherein the teaching adaptability data includes teaching effectiveness data, grade level adaptability data, and value score data.

4. The system according to claim 3, characterized in that, The teaching adaptability assessment module includes a teaching effectiveness assessment module. This module identifies teaching element information in the content to be assessed based on the content feature data, generates logical coherence data corresponding to the content to be assessed based on the teaching element information, determines the sentence length information, terminology density information, and number of logical connectors in the content to be assessed based on the content feature data, assesses the ease with which students learn the content to be assessed based on the length information, density information, and number of connectors, and obtains the cognitive load coefficient corresponding to the content to be assessed. Based on the logical coherence data and the cognitive load coefficient, it generates teaching effectiveness data within the teaching adaptability data.

5. The system according to claim 3, characterized in that, The teaching adaptability assessment module includes: a grade level adaptability assessment module; the grade level adaptability assessment module is used to determine the standard language content of the target grade level corresponding to the content to be assessed, and to evaluate the language style similarity based on the standard language content of the target grade level and the content to be assessed, so as to obtain the grade level adaptability data in the teaching adaptability data.

6. The system according to claim 3, characterized in that, The teaching adaptability assessment module includes a value assessment module; the value assessment module is used to identify key information and sensitive word information in the content to be assessed, and generate value score data in the teaching adaptability data based on the identification results.

7. The system according to claim 2, characterized in that, The fusion analysis module includes an effectiveness analysis module and a fusion analysis submodule. The effectiveness analysis module is connected to the content accuracy assessment module and the teaching adaptability assessment module, respectively, and the fusion analysis submodule is connected to the effectiveness analysis module. The effectiveness analysis module is used to perform effectiveness analysis on the content accuracy data sent by the content accuracy assessment module to obtain content effectiveness data, and then send the content effectiveness data to the fusion analysis submodule.

8. The system according to claim 7, characterized in that, The effectiveness analysis module is used to analyze the effectiveness of the teaching effectiveness data, the grade level fit data, and the value score data sent by the teaching adaptability assessment module, obtain teaching effectiveness data, and send the teaching effectiveness data to the fusion analysis submodule.

9. The system according to claim 8, characterized in that, The fusion analysis submodule is used to generate weighted data corresponding to the content accuracy data, the teaching effectiveness data, the grade level suitability data, and the value score data, respectively, based on the content effectiveness data and the teaching effectiveness data sent by the effectiveness analysis module. Based on the weighted data, the accuracy data of the content, the effectiveness data of the teaching, the suitability data of the learning stage, and the value score data are integrated and analyzed to obtain the quality assessment result of the content to be evaluated.

10. An electronic device, characterized in that, A text quality assessment system for educational databases as described in any one of claims 1 to 9.

Images