English outline vocabulary learning and expanding method intelligent system based on word source learning

Abstract

The invention discloses an English outline vocabulary expansion method based on word source learning and an intelligent system, and belongs to the cross technical field of artificial intelligence and computer-aided language learning. The method aims at solving the technical problems that an existing vocabulary learning tool neglects a word source rule and is not bound with a teaching outline, and generated content is uncontrollable due to the fact that a large language model is directly used. The method comprises the steps of obtaining an initial vocabulary and an expansion demand input by a user; querying word source composition information based on a pre-constructed English outline word source knowledge base; determining a target vocabulary grade range associated with the teaching outline according to requirements; screening from a knowledge base and / or generating a group of expansion vocabularies through a large language model under the double constraints of the grade range and the word source expansion direction; and outputting the expansion vocabulary and the structured analysis information thereof. The system comprises corresponding function modules. According to the method, the word source science law and the teaching outline requirement are converted into computable hard constraints, accurate guidance and control of the large language model generation process are achieved, and therefore a scientific, systematic and target-accurate vocabulary expansion scheme is provided, and the method is suitable for development of intelligent language teaching tools.

Description

Technical Field

[0001] This invention relates to the interdisciplinary field of artificial intelligence and computer-aided language learning, specifically to an etymological-based method for expanding English vocabulary and an intelligent system for implementing this method. This invention is particularly applicable to the core engine of building intelligent language teaching tools with adaptive capabilities. Background Technology

[0002] Mastering English vocabulary is the cornerstone of language proficiency. Traditional vocabulary learning methods mainly rely on rote memorization of word spelling, pronunciation, and corresponding Chinese definitions. However, as a phonetic language, English's vast vocabulary is composed of a limited number of roots, prefixes, and suffixes combined according to specific rules. Traditional methods ignore this inherent etymological and word-formation pattern, resulting in a tedious learning process, low memorization efficiency, and difficulty in forming a systematic vocabulary network, severely restricting the effective expansion of vocabulary.

[0003] With the development of educational technology, various electronic dictionary software and mobile vocabulary learning applications have emerged. While these existing solutions offer convenience to some extent, they still have significant limitations: First, their functions are mostly limited to providing isolated word definitions and example sentences, lacking clear and structured explanations of typical vocabulary usage, thus increasing the learner's inductive burden. Second, most tools lack in-depth analysis and visualization of word formation components from an etymological perspective, preventing learners from understanding the inherent logic of vocabulary derivation, and keeping learning superficial. Third, their vocabulary expansion or recommendation functions are mostly based on simple word frequency statistics, co-occurrence relationships, or broad semantic similarity calculations, failing to be deeply integrated with authoritative teaching syllabi with clear graded systems, such as the "General High School English Curriculum Standards" and the "National College English Test Band 4 and 6 Syllabus." This results in recommended expanded vocabulary often deviating from the learner's stage goals, potentially far exceeding their current cognitive level or irrelevant to their learning focus, making the learning path lack precise targeting and controllability.

[0004] In recent years, large-scale language models based on deep learning have demonstrated powerful capabilities in natural language processing tasks and have begun to be applied to educational support scenarios. However, when directly applied to open-ended vocabulary expansion tasks, they reveal an inherent flaw: "uncontrollable generated content." Because the generation mechanism of large language models is based on the probability distribution in their training corpus, the models tend to output semantically related but unconstrained words, which cannot be precisely and reliably limited to the finite vocabulary set and difficulty level defined by a specific teaching syllabus. Therefore, directly calling such models easily generates a large number of out-of-syllabus, obscure, or unsuitable words for the current learning stage, making it difficult to integrate them into professional learning systems as targeted and stable teaching components.

[0005] In summary, existing technologies have not yet effectively solved the problem of how to organically combine the scientific principles of etymology, the hierarchical target system of the teaching syllabus, and the intelligent generation capabilities of large-scale language models to achieve an intelligent vocabulary expansion scheme with predictable, constrained, and strictly aligned outputs that align with preset learning objectives. This is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0006] (a) Technical problems to be solved The present invention aims to overcome the above-mentioned defects of the prior art and solve the following technical problems: 1. How can vocabulary expansion methods go beyond isolated memorization and simple recommendations, incorporating systematic etymological analysis to improve learning efficiency and depth of understanding? 2. How to ensure that the vocabulary expansion process is strictly aligned with the precise grading system of the authoritative teaching syllabus, so as to achieve precise focus on learning objectives and rigid constraints on learning paths; 3. How to effectively guide and constrain the generation capabilities of large-scale language models so that when applied to vocabulary expansion tasks, the output can be strictly limited to the preset vocabulary range and difficulty level, thus solving the problem of uncontrollable AI-generated content. (II) Technical Solution To address the aforementioned technical problems, this invention provides an etymological-based method for expanding English syllabus vocabulary and a corresponding intelligent system. The core of this invention lies in constructing a technical framework that integrates a structured knowledge base, an interactive guided process, and a constrained intelligent generation engine. This framework transforms objective requirements from the teaching field (syllabus level) and linguistic rules (morpheme composition) into computable and coded hard constraints to guide and control the entire expansion process. According to one aspect of the present invention, an etymological-based method for expanding English syllabi vocabulary is provided, characterized by comprising the following steps: S1. Obtain the initial vocabulary and extended requirements input by the user; S2. Based on the pre-built English syllabus vocabulary etymology knowledge base, query the etymological composition information corresponding to the initial vocabulary, wherein the etymological composition information includes roots, prefixes and / or suffixes; S3. Based on the aforementioned extended requirements, determine a target vocabulary level range that is associated with a predefined English teaching syllabus; S4. Under the dual constraints of the target vocabulary level range and the etymological expansion direction determined based on the etymological composition information, a set of expanded vocabulary is selected from the English syllabus vocabulary etymological knowledge base and / or generated through a large language model; wherein, the expanded vocabulary and its parsing information are both limited to the target vocabulary level range. S5. Output the expanded vocabulary and its corresponding structured parsing information. Preferably, the entries in the English syllabus vocabulary etymology knowledge base contain at least three types of annotation information: vocabulary level information determined according to a predefined English teaching syllabus document, etymological composition information determined according to authoritative etymological materials, and vocabulary usage information determined according to authoritative learner's dictionaries. According to another aspect of the present invention, an intelligent system for implementing the above-described method is provided. This system can be implemented in software, hardware, or a combination of both, and includes: The input module is used to receive initial vocabulary and extended requirements from the user. The knowledge base module stores the etymological knowledge base of the English syllabus vocabulary, which is used to respond to queries and provide structured information about the vocabulary; The processing and control module is used to execute steps S2 to S4 of the method, specifically including: querying the knowledge base based on the information from the input module, determining the target vocabulary level range and the direction of word source expansion, and calling the filtering logic or the large language model interface under the dual constraints to generate expanded vocabulary; The output module is used to present the generated extended vocabulary and its structured parsing information to the user in a preset format. The processing and control module invokes the large language model by passing the target vocabulary level range, the etymological information, and the relevant structured information obtained from the knowledge base module as precise contextual hints and constraints to the large language model through the application programming interface, thereby driving it to perform reasoning and generation within the parameter space that conforms to the constraints, thus achieving precise guidance and control of the model generation process. (III) Beneficial Effects Compared with the prior art, the technical solution provided by the present invention has the following significant advantages: 1. Enhanced the scientific and systematic nature of vocabulary learning: By introducing a structured etymological knowledge base, isolated vocabulary memorization is transformed into systematic cognition and networked association based on word-forming components such as roots and affixes. This aligns with the human cognitive pattern of memorizing complex wholes by understanding their constituent parts, significantly strengthening the logical connections between words, facilitating the formation of long-term, stable memory networks, and fundamentally improving learning efficiency and memory retention. 2. Achieved precise focus on learning objectives and optimized resources: By forcibly linking the vocabulary expansion process with a clearly graded teaching syllabus, it ensures that all generated or recommended vocabulary is strictly limited to the learning stage selected by the learner or determined by the system. This solves the problems of content generalization, vague objectives, and cognitive overload inherent in traditional recommendation methods or general AI tools, making learning resources highly concentrated, learning paths clear and controllable, and greatly improving the relevance of learning and the effectiveness of time investment. 3. Overcoming the controllability challenge in applying artificial intelligence to vocabulary teaching: This invention creatively transforms domain-specific objective requirements (syllabus levels) and linguistic rules (morpheme composition) into computable and coded hard constraints, and injects them into the generation process of large-scale language models through carefully designed prompting instructions and context construction. This technical approach effectively "tames" the model's open-ended generation tendency, transforming its output from "free divergence" to "directed selection and organization under rigid rules," achieving a high degree of predictability, guidance, and pedagogical applicability of the generated results. This is a key technological breakthrough in transforming general artificial intelligence capabilities into reliable, specialized teaching tools. 4. Enhanced overall system efficiency and economy: A structured knowledge base, efficiently deployed locally or in the cloud, serves as the core data source, providing accurate, condensed, and highly relevant contextual information for large language models. This significantly reduces the computational overhead and time latency associated with broad semantic retrieval, irrelevant reasoning, and processing large numbers of irrelevant tokens during the generation process of large models. This improves system response speed and result accuracy while reducing long-term computational and API call costs.

Claims

1. A method for expanding English syllabus vocabulary based on etymology, characterized in that, Includes the following steps: S1. Obtain the initial vocabulary and extended requirements input by the user; S2. Based on the pre-built English syllabus vocabulary etymology knowledge base, query the etymological composition information corresponding to the initial vocabulary, wherein the etymological composition information includes roots, prefixes and / or suffixes; S3. Based on the aforementioned extended requirements, determine a target vocabulary level range that is associated with a predefined English teaching syllabus; S4. Under the dual constraints of the target vocabulary level range and the etymological expansion direction determined based on the etymological composition information, a set of expanded vocabulary is selected from the English syllabus vocabulary etymological knowledge base and / or generated through a large language model; wherein, the expanded vocabulary and its parsing information are both limited to the target vocabulary level range. S5. Output the expanded vocabulary and its corresponding structured parsing information.

2. The method according to claim 1, characterized in that, The vocabulary etymology knowledge base of the English syllabus contains at least three types of annotation information: vocabulary level information determined according to predefined English teaching syllabus documents, etymological composition information determined according to authoritative etymological materials, and vocabulary usage information determined according to authoritative learner's dictionaries.