English writing intelligent correcting and improving method and system based on big data analysis

Abstract

The invention relates to the technical field of intelligent teaching, and discloses an English writing intelligent correcting and improving method and system based on big data analysis, and the method comprises the steps: inputting a to-be-corrected English writing text into a multi-dimensional evaluation model, and obtaining an English writing evaluation result, a real-time diagnosis report containing logic fault positioning, defect type labeling and vocabulary replacement suggestions is generated according to the English writing evaluation result; according to the real-time diagnosis report, associating high-frequency error modes in the historical writing data of the student, and generating a personalized learning path; and based on the writing task type of the English writing text to be corrected, determining a weight priority according to the writing genuine characteristics, screening a target strategy combination from the personalized learning path according to the weight priority, and generating a lifting scheme matched with the writing task type. According to the invention, the defects of a traditional correction mode are overcome, targeted improvement guidance is provided for students, and the quality and efficiency of English writing teaching and learning are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent teaching technology, and in particular to a method and system for intelligent correction and improvement of English writing based on big data analysis. Background Art

[0002] In the teaching and learning of English writing, traditional grading methods have many shortcomings. Manual grading is time-consuming and labor-intensive, and it is difficult for teachers to conduct detailed and comprehensive grading of a large number of student assignments. In addition, subjective factors affect the objectivity of the grading results. Some existing English writing assistance software has relatively basic grading functions and can only identify simple grammatical errors and spelling errors. It is difficult to give accurate and targeted evaluations of the logical structure, content depth, vocabulary richness, etc. of the article. When analyzing writing problems, they lack in-depth mining and learning of large amounts of writing data, and cannot provide personalized improvement suggestions based on the learning characteristics and writing levels of different students. In addition, these software do not provide sufficient support for the diversity of English writing. For writing tasks of different types and requirements, they cannot flexibly adapt to the corresponding grading standards and improvement strategies, and cannot meet the diverse needs of students and teachers in English writing teaching and learning, which limits the effective improvement of English writing levels.

[0003] Therefore, it is urgent to provide a technical solution to solve the above problems. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method, system, electronic device and storage medium for intelligent correction and improvement of English writing based on big data analysis.

[0005] In a first aspect, the present invention provides a method for intelligent correction and improvement of English writing based on big data analysis. The technical solution of the method is as follows:

[0006] Inputting an English writing text to be corrected into a multi-dimensional evaluation model to obtain an English writing evaluation result for the English writing text to be corrected, and generating a real-time diagnostic report based on the English writing evaluation result, including logical fault location, defect type annotation, and vocabulary replacement suggestions; wherein the English writing evaluation result includes: logical structure score, content depth level, and vocabulary complexity distribution;

[0007] Correlating high-frequency error patterns in students' historical writing data based on the real-time diagnostic report to generate a personalized learning path;

[0008] Based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics, the weight priorities of the logical structure score, the content depth level and the vocabulary complexity distribution are determined, and according to the weight priorities, the target strategy combination is screened from the personalized learning path to generate an improvement plan that matches the writing task type.

[0009] The beneficial effects of the intelligent correction and improvement method for English writing based on big data analysis of the present invention are as follows:

[0010] The method of the present invention uses a multi-dimensional evaluation model to evaluate English writing texts to be corrected, generating a real-time diagnostic report that includes logical fault location, defect type annotation, and vocabulary replacement suggestions. This addresses the time-consuming and labor-intensive, highly subjective nature of traditional correction methods, as well as the shortcomings of existing software correction functions that are basic and incapable of accurately evaluating deep-seated problems in articles. At the same time, it associates students' historical writing data to generate personalized learning paths, determines weight priorities based on writing task types and writing genre characteristics, and screens target strategy combinations to generate improvement plans. This meets the diverse needs of different writing tasks in English writing teaching and learning, improves the effectiveness of English writing proficiency, provides students with targeted improvement guidance, and improves the quality and efficiency of English writing teaching and learning.

[0011] On the basis of the above scheme, the intelligent correction and improvement method of English writing based on big data analysis of the present invention can also be improved as follows.

[0012] In an optional manner, the method further includes:

[0013] Based on the massive corpus in the historical writing database, hierarchical features of logical structure, content depth, and vocabulary richness are extracted, and the multidimensional evaluation model containing the hierarchical features is established; wherein, the input of the multidimensional evaluation model is the semantic features of the English writing text to be corrected, and the output is the English writing evaluation result including the logical structure score, content depth level and vocabulary complexity distribution.

[0014] In an optional embodiment, the step of generating a real-time diagnostic report including logical fault location, defect type annotation, and vocabulary replacement suggestions based on the English writing evaluation results further includes:

[0015] Determining the location of the logical fault in the English writing text to be corrected based on the logical structure score;

[0016] Determining the defect type label in the English writing text to be corrected according to the content depth level;

[0017] The vocabulary replacement suggestion in the English writing text to be corrected is determined based on the vocabulary complexity distribution.

[0018] In an optional embodiment, the personalized learning path includes: a logic chain reconstruction template, argument reinforcement examples, and a domain-adapted vocabulary library; the step of generating a personalized learning path based on the real-time diagnostic report and associating high-frequency error patterns in students' historical writing data further includes:

[0019] According to the logical fault location, the defect type annotation and the vocabulary replacement suggestions in the real-time diagnostic report, the high-frequency error patterns in the student's historical writing data are associated to generate the logical chain reconstruction template corresponding to the logical fault location, the argument reinforcement example matching the defect type annotation and the domain-adapted vocabulary library based on the vocabulary replacement suggestions to form the personalized learning path.

[0020] In an optional manner, the step of determining the weight priorities of the logical structure score, the content depth level, and the vocabulary complexity distribution based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics further includes:

[0021] Based on the writing task type of the English writing text to be corrected, and in accordance with the writing genre characteristics of academic papers, creative writing, and business correspondence, the weight priorities of the logical structure score, the content depth level, and the vocabulary complexity distribution are determined; wherein the weight priorities are directly associated with the writing genre characteristics, with academic papers having the highest weight corresponding to the content depth level, creative writing having the highest weight corresponding to the logical structure score, and business correspondence having the highest weight corresponding to the vocabulary complexity distribution.

[0022] In an optional manner, the step of screening target strategy combinations from the personalized learning path according to the weight priority and generating an improvement plan matching the writing task type further includes:

[0023] Based on the weight priority, a target strategy combination that meets the logical structure score, content depth level and vocabulary complexity distribution is screened from the personalized learning path to generate the improvement plan that matches the writing task type.

[0024] In a second aspect, the present invention provides an intelligent English writing correction and improvement system based on big data analysis. The technical solution of the system is as follows:

[0025] An acquisition module is configured to input an English writing text to be graded into a multi-dimensional evaluation model, obtain an English writing evaluation result for the English writing text to be graded, and generate a real-time diagnostic report based on the English writing evaluation result, including logical fault location, defect type annotation, and vocabulary replacement suggestions; wherein the English writing evaluation result includes: logical structure score, content depth level, and vocabulary complexity distribution;

[0026] a generation module for correlating high-frequency error patterns in students' historical writing data based on the real-time diagnostic report to generate a personalized learning path;

[0027] The running module is used to determine the weight priority of the logical structure score, the content depth level and the vocabulary complexity distribution based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics, and according to the weight priority, screen the target strategy combination from the personalized learning path to generate an improvement plan that matches the writing task type.

[0028] The beneficial effects of the intelligent English writing correction and improvement system based on big data analysis of the present invention are as follows:

[0029] The system of the present invention uses a multi-dimensional evaluation model to evaluate English writing texts to be corrected, generating real-time diagnostic reports that include logical fault location, defect type annotation, and vocabulary replacement suggestions. This addresses the time-consuming and labor-intensive nature of traditional correction methods, as well as the shortcomings of existing software correction functions, which are basic and incapable of accurately evaluating the underlying problems of the article. At the same time, it links students' historical writing data to generate personalized learning paths, determines weight priorities based on writing task types and writing genre characteristics, and screens target strategy combinations to generate improvement plans. This meets the diverse needs of different writing tasks in English writing teaching and learning, improves the effectiveness of English writing proficiency, provides students with targeted improvement guidance, and improves the quality and efficiency of English writing teaching and learning.

[0030] On the basis of the above scheme, the intelligent correction and improvement system for English writing based on big data analysis of the present invention can also be improved as follows.

[0031] In an optional manner, the method further includes:

[0032] A construction module is used to extract hierarchical features of logical structure, content depth, and vocabulary richness based on the massive corpus in the historical writing database, and establish the multidimensional evaluation model containing the hierarchical features; wherein the input of the multidimensional evaluation model is the semantic features of the English writing text to be corrected, and the output is the English writing evaluation result including the logical structure score, content depth level and vocabulary complexity distribution.

[0033] In a third aspect, the technical solution of an electronic device of the present invention is as follows:

[0034] The system comprises a memory, a processor and a program stored in the memory and running on the processor. When the processor executes the program, the steps of the method for intelligent correction and improvement of English writing based on big data analysis of the present invention are implemented.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium having the following technical solution:

[0036] Instructions are stored in the computer-readable storage medium. When the computer-readable storage medium reads the instructions, the computer-readable storage medium executes the steps of the method for intelligent correction and improvement of English writing based on big data analysis of the present invention.

[0037] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0039] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0040] Figure 1 1. A flowchart of an embodiment of a method for intelligently correcting and improving English writing based on big data analysis according to the present invention;

[0041] Figure 2 This is a schematic structural diagram of an embodiment of an intelligent English writing correction and improvement system based on big data analysis according to the present invention;

[0042] Figure 3 The figure is a schematic structural diagram of an embodiment of an electronic device of the present invention. DETAILED DESCRIPTION

[0043] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0044] Figure 1The flowchart of an embodiment of a method for intelligent correction and improvement of English writing based on big data analysis provided by the present invention is shown. The method for intelligent correction and improvement of English writing based on big data analysis can be executed by electronic devices such as terminal devices or servers. The terminal device can be any fixed or mobile terminal such as user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. The server can be a single server or a server cluster composed of multiple servers. Any electronic device can implement the method for intelligent correction and improvement of English writing based on big data analysis by calling computer-readable instructions stored in the memory through the processor. As Figure 1 As shown, the following steps are included:

[0045] S1. Input an English writing text to be corrected into a multi-dimensional evaluation model to obtain an English writing evaluation result of the English writing text to be corrected, and generate a real-time diagnostic report including logical fault location, defect type labeling, and vocabulary replacement suggestions based on the English writing evaluation result.

[0046] The "ungraded English writing text" is the English writing text that needs to be graded in this embodiment. The multidimensional evaluation model is an evaluation model constructed using a machine learning algorithm. The input of the multidimensional evaluation model is the semantic features of the ungraded English writing text, and the output of the multidimensional evaluation model is the English writing evaluation results including the logical structure score, content depth level, and vocabulary complexity distribution.

[0047] It should be noted that: ① Logical structure score refers to the comprehensive score of the logical coherence of the quantitative text. 11 ·S 11 +w 12 ·S 12 +w 13 ·S 13 ; S1 represents the logical structure score, with a value of 0-100; w 11 、w 12 and w 13 The weight of the logical structure score is 1; S 11 is the density of transition words between paragraphs (the default is: the number of transition words per thousand words × 10), S 12 The completeness of the argument tree (default: the number of main argument and sub-argument levels × 20), S 13The degree of correspondence between the conclusion paragraph and the argument (the default is: 0-1 similarity × 100). ② Content depth level refers to the level divided by the diversity and innovation of the arguments, and the default value is L1-L5. The specific grading standards are shown in Table 1. ③ Vocabulary complexity distribution refers to the statistical distribution of the proportion of basic vocabulary, academic vocabulary, and professional terms in the text. ④ Logical fault positioning refers to identifying the specific location of logical breaks between paragraphs or sentences in the text based on the logical structure score and through semantic correlation analysis and logical conjunction detection. ⑤ Defect type annotation refers to classifying argument defects according to the content depth level and marking the specific defect location in the text. ⑥ Vocabulary replacement suggestions refer to screening low-complexity vocabulary based on vocabulary complexity distribution and providing a synonym replacement word list.

[0048] Table 1:

[0049] grade Number of argument types Innovation index (similarity with similar texts) L1 ≤2 ＞0.8 L2 3 0.6-0.8 L3 4 0.4-0.6 L4 ≥5 0.2-0.4 L5 ≥5 ＜0.2

[0050] In an optional manner, the method further includes:

[0051] Based on the massive corpus in the historical writing database, hierarchical features of logical structure, content depth, and vocabulary richness are extracted, and the multidimensional evaluation model containing the hierarchical features is established.

[0052] Specifically: ① The corpus in the historical writing database was segmented, tagged with parts of speech, and subjected to syntactic dependency analysis. ② A hierarchical feature extraction process was performed, sequentially extracting logical structure features (cohesion strength x1 and structural integrity x2), content depth features (argument diversity x3 and innovation index x4), and lexical richness features (repeated word ratio x5 and synonym substitution rate x6). ③ A random forest algorithm was used, with the input feature vector X = [x1, x2, x3, x4, x5, x6], to output the logical structure score, content depth level, and lexical complexity distribution. ④ Feature weighting: A grid search was performed to determine the optimal weight combination (e.g., a logical structure score weight of 0.4, a content depth level weight of 0.35, and a lexical complexity distribution weight of 0.25).

[0053] It should be noted that cohesion strength represents the density of transition words (number of transition words / total number of words × 100); structural integrity represents the hierarchical depth of the main argument and sub-arguments (e.g., a three-level argument tree = 3 points); argument diversity represents the number of types of statistical data, cases, and citations; the innovation index represents the cosine similarity with similar texts calculated by TF-IDF vectors; the proportion of repeated words represents the ratio of the number of repeated words to the total number of words; and the synonym substitution rate represents the ratio of the number of synonym pairs to the total number of sentences.

[0054] In an optional embodiment, the step of generating a real-time diagnostic report including logical fault location, defect type annotation, and vocabulary replacement suggestions based on the English writing evaluation results further includes:

[0055] The logical fault location in the English writing text to be corrected is determined based on the logical structure score.

[0056] Among them, when the logical structure score S1 is less than the corresponding threshold (such as 60), if S 11 <40, focus on detecting missing transition words between paragraphs; if S 12 <50, focus on analyzing the breakdown of the argument level; S 13 <30, it marks the semantic deviation between the conclusion and the argument. The cohesion strength and similarity threshold are adjusted dynamically, and the S 11 If S 12 If the score is less than 50, the argument tree hierarchy (e.g., main argument - sub-arguments - supporting evidence) is forced to be traversed, marking the location of missing levels (e.g., "No data support for sub-argument 2"). Based on the sub-logical structure score of each paragraph, paragraphs with sub-logical structure scores below the threshold are prioritized for marking, ultimately generating a logical fault location.

[0057] The defect type label in the English writing text to be corrected is determined according to the content depth level.

[0058] Different levels of content depth correspond to different defect types, and each defect type has corresponding annotation rules. When the content depth level is L1, the defect type is "the argument lacks data support," and an example annotation rule is "annotate the location of the argument sentence without data references." When the content depth level is L2, the defect type is "the evidence is loosely connected to the argument," and an example annotation rule is "annotate the paragraph where the case does not echo the argument." When the content depth level is L3 or above, the defect type is "the argument structure is incomplete," and an example annotation rule is "annotate the location where the conclusion paragraph does not summarize the sub-arguments."

[0059] The vocabulary replacement suggestion in the English writing text to be corrected is determined based on the vocabulary complexity distribution.

[0060] For each word ω in the English writing text to be corrected, the complexity score C is calculated ω = 0.6·CEFR(ω)+0.4·Tern(ω); CEFR(ω) represents the CEFR level of vocabulary ω (e.g. A1=1, C2=6); Tern(ω) represents the professional term matching flag (1=matched term base, 0=unmatched). Filter C ω <C avg -0.2 vocabulary (C avg is the average complexity of texts of the same genre), select C' from the synonym database ω ≥C avg For example, the C ω =1.2, C avg=2.0, the word replacement suggestion is "detrimental" (C' ω =2.8).

[0061] S2. Based on the real-time diagnostic report, correlate the high-frequency error patterns in the student's historical writing data and generate a personalized learning path.

[0062] Among them, the personalized learning path includes: logical chain reconstruction templates, argument reinforcement examples and domain-adaptive vocabulary libraries. The logical chain reconstruction template refers to a standardized correction framework generated for locating logical faults, including transition sentence templates and structural reorganization rules. The argument reinforcement example refers to a correction example library that matches the defect type annotation, including the original defect text, the revised version and annotations. The domain-adaptive vocabulary library refers to a collection of terms generated based on vocabulary replacement suggestions, classified by writing type (academic, creative, business).

[0063] Among them, the high-frequency error pattern in students' history writing data refers to the repetitive error patterns obtained from the statistics of students' history writing data, which are classified according to error type, frequency and contextual characteristics. Specifically: the quantification of error types includes: ① Sentence errors: subject-verb inconsistency F1, tense confusion F2; ② Argumentation defects: insufficient evidence F3, vague arguments F4; ③ Vocabulary misuse: terminology confusion F5, collocation error F6. If the frequency of an error in students' history writing data is greater than the corresponding threshold (such as 5 times / 10,000 words), it is marked as a high-frequency error; a weight vector is generated according to the error type.

[0064] In an optional embodiment, the step of generating a personalized learning path by associating high-frequency error patterns in the student's historical writing data based on the real-time diagnostic report further includes:

[0065] According to the logical fault location L1, the defect type annotation L2 and the vocabulary replacement suggestion L3 in the real-time diagnostic report, the high-frequency error patterns in the student's historical writing data are associated to generate the logical chain reconstruction template corresponding to the logical fault location, the argument reinforcement example matching the defect type annotation and the domain-adapted vocabulary library based on the vocabulary replacement suggestion to form the personalized learning path.

[0066] Specifically, the weight vector is loaded from the historical database according to the student ID Filter the top k errors with the highest weight (e.g., k=3). Locate each fault region in L1 for the logical fault and select the matching transition sentence template: ① Matching rule: fault type (e.g., causal fault) → template label (e.g., "causal connection template"); ② Priority adjustment: If If F3 is the highest, then the weight of the "data support template" corresponding to the insufficient evidence F3 will be increased.

[0067] Among them, for each defect type label in the defect type annotation L2, calculate the matching degree with the example library. If it is greater than the threshold, it is matched according to the historical error weight. Sort output.

[0068] Among them, according to the target field (such as academic papers) in the vocabulary replacement suggestion L3, the terms are filtered according to the formula: V term ={ω|C ω ≥C avg +δ]; δ is set dynamically according to the type of writing task, such as δ = 0.3 for academic papers.

[0069] S3. Based on the writing task type of the English writing text to be corrected and in accordance with the writing genre characteristics, determine the weight priority of the logical structure score, the content depth level, and the vocabulary complexity distribution, and based on the weight priority, screen the target strategy combination from the personalized learning path to generate an improvement plan that matches the writing task type.

[0070] Writing genre characteristics refer to the standardized attributes of different writing styles in terms of structure, language style, and content requirements, and serve as the core basis for evaluating and guiding writing. Writing task types are specific categories based on the purpose and context of the writing, which determine the focus of evaluation dimensions and the direction of improvement strategies. The target strategy combination refers to a collection of targeted improvement tools selected from the personalized learning path based on the writing task type and priority.

[0071] In an optional manner, the step of determining the weight priorities of the logical structure score, the content depth level, and the vocabulary complexity distribution based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics further includes:

[0072] Based on the writing task type of the English writing text to be corrected, and according to the writing genre characteristics of academic papers, creative writing, and business letters, the weight priorities of the logical structure score, the content depth level, and the vocabulary complexity distribution are determined.

[0073] Among them, the weight priority is directly related to the writing genre characteristics. Academic papers have the highest weight corresponding to the content depth level, creative writing has the highest weight corresponding to the logical structure score, and business letters have the highest weight corresponding to the vocabulary complexity distribution.

[0074] Specifically, based on the semantic features of the text to be reviewed (e.g., term density for academic papers, metaphors for creative writing, and conciseness metrics for business correspondence), a pre-trained classification model (e.g., BERT+Softmax) is used to output the writing task type. Based on the writing task type (academic paper, creative writing, business correspondence), weights are extracted from a pre-set type-weight rule library. For example, if the writing task type is academic, the corresponding weights for the logical structure score, content depth level, and vocabulary complexity distribution are [0.3, 0.5, 0.2].

[0075] In an optional manner, the step of screening target strategy combinations from the personalized learning path according to the weight priority and generating an improvement plan matching the writing task type further includes:

[0076] Based on the weight priority, a target strategy combination that meets the logical structure score, content depth level and vocabulary complexity distribution is screened from the personalized learning path to generate the improvement plan that matches the writing task type.

[0077] Specifically, the weights corresponding to the weight priority are [0.3, 0.5, 0.2], and the threshold corresponding to the logical structure score in the target strategy combination is T 逻辑 =0.3*reference threshold coefficient, T 逻辑 Used to filter the complexity of the logic chain reconstruction template; the range L corresponding to the content depth level min =0.5*grade coefficient, L min For the minimum grade requirement, if the grade coefficient is 5, L min =2.5, in this case only argument examples with level ≥3 are selected; lexical complexity distribution δ 词汇 = 0.2*domain adjustment coefficient, used to control term level, the default domain adjustment coefficient is 0.6. Select S1≥T from the personalized learning path 逻辑 Logical chain template, filter content depth level L≥L min And the demonstration example with a matching degree of ≥0.8 with the defect type annotation, extract the term level C from the domain adaptation vocabulary library ω ≥C avg +δ 词汇 The improvement plan for matching writing task types includes: selected logic chain templates, argument examples, and vocabulary database.

[0078] The technical solution of this embodiment uses a multi-dimensional evaluation model to evaluate the English writing text to be corrected, generating a real-time diagnostic report that includes logical fault location, defect type annotation, and vocabulary replacement suggestions. This solves the shortcomings of traditional correction methods, which are time-consuming and labor-intensive, highly subjective, and the basic correction functions of existing software, which cannot accurately evaluate the deep-seated problems of the article. At the same time, it associates students' historical writing data to generate personalized learning paths, determines weight priorities based on the type of writing task and the characteristics of the writing genre, and screens target strategy combinations to generate improvement plans. This meets the diverse needs of different writing tasks in English writing teaching and learning, improves the effectiveness of English writing proficiency, provides students with targeted improvement guidance, and improves the quality and efficiency of English writing teaching and learning.

[0079] Figure 2 FIG2 shows a schematic diagram of an embodiment of an intelligent English writing correction and improvement system 200 based on big data analysis provided by the present invention. Figure 2 As shown, the system 200 includes: an acquisition module 210, a generation module 220 and an operation module 230;

[0080] The acquisition module 210 is configured to input the English writing text to be corrected into the multi-dimensional evaluation model, obtain the English writing evaluation results of the English writing text to be corrected, and generate a real-time diagnostic report based on the English writing evaluation results, including logical fault location, defect type annotation, and vocabulary replacement suggestions; wherein the English writing evaluation results include: logical structure score, content depth level, and vocabulary complexity distribution;

[0081] A generating module 220 is configured to generate a personalized learning path based on the real-time diagnostic report and correlating high-frequency error patterns in the student's historical writing data;

[0082] The operation module 230 is used to determine the weight priority of the logical structure score, the content depth level and the vocabulary complexity distribution based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics, and according to the weight priority, screen the target strategy combination from the personalized learning path to generate an improvement plan that matches the writing task type.

[0083] In an optional manner, the method further includes:

[0084] A construction module is used to extract hierarchical features of logical structure, content depth, and vocabulary richness based on the massive corpus in the historical writing database, and establish the multidimensional evaluation model containing the hierarchical features; wherein the input of the multidimensional evaluation model is the semantic features of the English writing text to be corrected, and the output is the English writing evaluation result including the logical structure score, content depth level and vocabulary complexity distribution.

[0085] In an optional manner, the acquisition module 210 is specifically configured to:

[0086] Determining the location of the logical fault in the English writing text to be corrected based on the logical structure score;

[0087] Determining the defect type label in the English writing text to be corrected according to the content depth level;

[0088] The vocabulary replacement suggestion in the English writing text to be corrected is determined based on the vocabulary complexity distribution.

[0089] In an optional manner, the personalized learning path includes: a logic chain reconstruction template, argument reinforcement examples, and a domain-adapted vocabulary library; the generation module 220 is specifically used to:

[0090] According to the logical fault location, the defect type annotation and the vocabulary replacement suggestions in the real-time diagnostic report, the high-frequency error patterns in the student's historical writing data are associated to generate the logical chain reconstruction template corresponding to the logical fault location, the argument reinforcement example matching the defect type annotation and the domain-adapted vocabulary library based on the vocabulary replacement suggestions to form the personalized learning path.

[0091] In an optional manner, the operation module 230 is specifically configured to:

[0092] Based on the writing task type of the English writing text to be corrected, and in accordance with the writing genre characteristics of academic papers, creative writing, and business correspondence, the weight priorities of the logical structure score, the content depth level, and the vocabulary complexity distribution are determined; wherein the weight priorities are directly associated with the writing genre characteristics, with academic papers having the highest weight corresponding to the content depth level, creative writing having the highest weight corresponding to the logical structure score, and business correspondence having the highest weight corresponding to the vocabulary complexity distribution.

[0093] In an optional manner, the operation module 230 is specifically configured to:

[0094] Based on the weight priority, a target strategy combination that meets the logical structure score, content depth level and vocabulary complexity distribution is screened from the personalized learning path to generate the improvement plan that matches the writing task type.

[0095] It should be noted that the beneficial effects of the English writing intelligent correction and improvement system 200 based on big data analysis provided by the above embodiment are the same as the beneficial effects of the English writing intelligent correction and improvement method based on big data analysis, which will not be repeated here. In addition, when the system provided by the above embodiment realizes its functions, it only uses the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0096] Among them, the intelligent correction and improvement system 200 for English writing based on big data analysis of the present invention can be a computer program (including program code) running in a computer device. For example, the intelligent correction and improvement system for English writing based on big data analysis of the present invention is an application software that can be used to execute the corresponding steps in the intelligent correction and improvement method for English writing based on big data analysis of the present invention.

[0097] In some embodiments, the intelligent correction and improvement system for English writing based on big data analysis of the present invention can be implemented by a combination of software and hardware. As an example, the intelligent correction and improvement system for English writing based on big data analysis of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the intelligent correction and improvement method for English writing based on big data analysis of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs) or other electronic components.

[0098] The modules described in the embodiments of the present invention may be implemented in software or hardware, and the name of a module does not necessarily limit the module itself.

[0099] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the above-mentioned methods for intelligently correcting and improving English writing based on big data analysis is implemented. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to, a processor and a memory; the memory is used to store the computer program; and the processor is used to execute the method for intelligently correcting and improving English writing based on big data analysis shown in any one of the embodiments of the present invention by calling the computer program.

[0100] In an alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0101] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0102] Bus 4002 may include a path for transmitting information between the above components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3In the figure, only one thick line is used to represent the bus 4002, but this does not mean that there is only one bus or one type of bus.

[0103] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0104] The memory 4003 is used to store application code (computer program) for executing the solution of the present invention, and is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0105] Among them, the electronic device can also be a terminal device, and the terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, smart TV, and smart car-mounted device.

[0106] It should be noted that Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0107] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements any of the above-mentioned methods for intelligent correction and improvement of English writing based on big data analysis.

[0108] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0109] In an exemplary embodiment, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned method for intelligent correction and improvement of English writing based on big data analysis.

[0110] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0111] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0112] The computer-readable storage medium provided in the embodiments of the present invention may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or component.

[0113] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0114] The above description is merely a preferred embodiment of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present invention.

[0115] It should be noted that the terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and to define a specific order or precedence. Where appropriate, the order used for similar objects may be interchanged, such that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0116] Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention may be implemented in the form of a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0117] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An intelligent correction and improvement method for English writing based on big data analysis, characterized by: The method comprises: Inputting an English writing text to be corrected into a multi-dimensional evaluation model to obtain an English writing evaluation result for the English writing text to be corrected, and generating a real-time diagnostic report based on the English writing evaluation result, including logical fault location, defect type annotation, and vocabulary replacement suggestions; wherein the English writing evaluation result includes: logical structure score, content depth level, and vocabulary complexity distribution; Correlating high-frequency error patterns in students' historical writing data based on the real-time diagnostic report to generate a personalized learning path; Based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics, the weight priorities of the logical structure score, the content depth level and the vocabulary complexity distribution are determined, and according to the weight priorities, the target strategy combination is screened from the personalized learning path to generate an improvement plan that matches the writing task type.

2. The method for intelligent correction and improvement of English writing based on big data analysis according to claim 1 is characterized in that: Also includes: Based on the massive corpus in the historical writing database, hierarchical features of logical structure, content depth, and vocabulary richness are extracted, and the multidimensional evaluation model containing the hierarchical features is established; wherein, the input of the multidimensional evaluation model is the semantic features of the English writing text to be corrected, and the output is the English writing evaluation result including the logical structure score, content depth level and vocabulary complexity distribution.

3. The method for intelligent correction and improvement of English writing based on big data analysis according to claim 2 is characterized in that: The step of generating a real-time diagnostic report including logical fault location, defect type annotation, and vocabulary replacement suggestions based on the English writing evaluation results further includes: Determining the location of the logical fault in the English writing text to be corrected based on the logical structure score; Determining the defect type label in the English writing text to be corrected according to the content depth level; The vocabulary replacement suggestion in the English writing text to be corrected is determined based on the vocabulary complexity distribution.

4. The method for intelligent correction and improvement of English writing based on big data analysis according to claim 1 is characterized in that: The personalized learning path includes: a logic chain reconstruction template, an argument reinforcement paradigm, and a domain-adapted vocabulary library; the step of generating a personalized learning path based on the real-time diagnostic report and associating high-frequency error patterns in students' historical writing data further includes: According to the logical fault location, the defect type annotation and the vocabulary replacement suggestions in the real-time diagnostic report, the high-frequency error patterns in the student's historical writing data are associated to generate the logical chain reconstruction template corresponding to the logical fault location, the argument reinforcement example matching the defect type annotation and the domain-adapted vocabulary library based on the vocabulary replacement suggestions to form the personalized learning path.

5. The method for intelligent correction and improvement of English writing based on big data analysis according to claim 1 is characterized in that: The step of determining the weight priority of the logical structure score, the content depth level, and the vocabulary complexity distribution based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics further includes: Based on the writing task type of the English writing text to be corrected, and in accordance with the writing genre characteristics of academic papers, creative writing, and business correspondence, the weight priorities of the logical structure score, the content depth level, and the vocabulary complexity distribution are determined; wherein the weight priorities are directly associated with the writing genre characteristics, with academic papers having the highest weight corresponding to the content depth level, creative writing having the highest weight corresponding to the logical structure score, and business correspondence having the highest weight corresponding to the vocabulary complexity distribution.

6. The method for intelligent correction and improvement of English writing based on big data analysis according to claim 5 is characterized in that: The step of screening target strategy combinations from the personalized learning path according to the weight priority and generating an improvement plan matching the writing task type further includes: Based on the weight priority, a target strategy combination that meets the logical structure score, content depth level and vocabulary complexity distribution is screened from the personalized learning path to generate the improvement plan that matches the writing task type.

7. An intelligent English writing correction and improvement system based on big data analysis, characterized by: The system comprises: An acquisition module is configured to input an English writing text to be graded into a multi-dimensional evaluation model, obtain an English writing evaluation result for the English writing text to be graded, and generate a real-time diagnostic report based on the English writing evaluation result, including logical fault location, defect type annotation, and vocabulary replacement suggestions; wherein the English writing evaluation result includes: logical structure score, content depth level, and vocabulary complexity distribution; a generation module for correlating high-frequency error patterns in students' historical writing data based on the real-time diagnostic report to generate a personalized learning path; The running module is used to determine the weight priority of the logical structure score, the content depth level and the vocabulary complexity distribution based on the writing task type of the English writing text to be corrected and according to the writing genre characteristics, and according to the weight priority, screen the target strategy combination from the personalized learning path to generate an improvement plan that matches the writing task type.

8. The intelligent English writing correction and improvement system based on big data analysis according to claim 7 is characterized in that: Also includes: A construction module is used to extract hierarchical features of logical structure, content depth, and vocabulary richness based on the massive corpus in the historical writing database, and establish the multidimensional evaluation model containing the hierarchical features; wherein the input of the multidimensional evaluation model is the semantic features of the English writing text to be corrected, and the output is the English writing evaluation result including the logical structure score, content depth level and vocabulary complexity distribution.

9. An electronic device, characterized in that: The electronic device includes a processor, which is coupled to a memory. The memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor, so that the electronic device implements the intelligent correction and improvement method for English writing based on big data analysis as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one computer program, which is loaded and executed by the processor so that the computer-readable storage medium implements the intelligent correction and improvement method for English writing based on big data analysis as described in any one of claims 1 to 6.

Images