Intelligent education resource management system and method based on cloud platform

Abstract

The invention relates to the technical field of educational resource management, and discloses an intelligent educational resource management system and method based on a cloud platform, which are used for solving the problem that when multiple versions of resumes exist in the system, the most suitable post resume cannot be quickly and accurately selected, and the method comprises the following steps: recording each learning resource access of students; students edit resumes through a resume editing interface, directly upload the learning completion condition data in the resumes and store the resumes edited each time into a resume database, teachers screen out postable posts, and for each postable post, resume data of each version is obtained. The resume data comprises the resume content, the updating time point and the historical delivery record, the delivery matching index is obtained through resume data evaluation, the resume most suitable for delivery is screened out according to the delivery matching index and delivered, the matching degree of the resume and the post is effectively improved, and the interview success rate of students is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of educational resource management, and more specifically to an intelligent educational resource management system and method based on a cloud platform. Background Art

[0002] Intelligent educational resource management is a key area of ​​current educational informatization development. It is widely used in universities, vocational schools, and various training institutions to support multiple stages, including curriculum development, teaching organization, learning process analysis, student ability assessment, and job matching. With the deepening advancement of the "Internet + Education" model, cloud-based educational resource management systems have gradually achieved standardized organization of teaching content, process-based tracking of learning behaviors, and intelligent feedback from data analysis, becoming a key support platform for teaching activities.

[0003] In the intelligent education platform system, the employment module serves as a key link between "education and employment," and one of its core functions is student resume management. Traditional resume management methods, mostly based on static uploads and manual review, are unable to adapt to the rapid changes in job requirements and the actual needs of configuring multiple resume versions for multiple positions. As job classifications become increasingly refined and employer reviews become more intelligent, students often need to create multiple resume versions for different job directions (such as R&D, design, marketing, etc.) to highlight their respective strengths.

[0004] For example, the invention patent with publication number CN118643224A discloses a cloud resource management system for an online education platform based on intelligent analysis. The system adopts random forest models and fuzzy logic control technology to achieve efficient management and dynamic allocation of educational resources. Through in-depth analysis of user behavior and system performance, the system can accurately predict future resource needs and adjust resource allocation in real time based on these predictions, thereby optimizing resource utilization and improving service quality. In addition, the system also includes content recommendation and preloading functions, which predict and load content that users may be interested in based on their behavior patterns, significantly improving user experience and system response speed. The present invention significantly improves the operating efficiency and user satisfaction of online education platforms through intelligent resource management, and has important practical value.

[0005] However, the above technology has at least the following technical problems:

[0006] In actual applications, a student may edit multiple versions of his or her resume for multiple positions. In intelligent educational resource management, the system cannot quickly and accurately select the corresponding resume from multiple resume versions for submission, resulting in a decrease in job suitability, affecting the accuracy of the job recommendation results of the educational resource management system and the student's interview success rate. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent educational resource management system and method based on a cloud platform to solve the problems existing in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The intelligent education resource management system based on the cloud platform includes: a user and authority management module, which is used to authenticate the user identity through the account registration information when registering an account, and to identify the user authority through the account information when the user logs in. The user identities include teachers, students and enterprises; a course and learning resource management module, which is used to allow teachers to create courses, upload courseware, organize chapter structures, and build associations between micro-videos and chapter tests according to their authority after identifying the user authority; students to access learning resources according to their authority; a learning process and evaluation module, which records each student's access to learning resources and obtains learning completion status data; an employment and enterprise docking module, which is used to A resume editing interface is provided, and students can edit their resumes through the resume editing interface, and can directly upload learning completion data in the resume, and store each edited resume in the resume database; teachers screen out available positions, and for each available position, obtain each version of resume data. The resume data includes resume content, update time point, and historical delivery records. The delivery matching index is obtained based on the resume data evaluation, and the most suitable resume is screened out based on the delivery matching index and delivered; the message and notification management module is used to push corresponding reminders based on the user account identity; the knowledge support module is used to build a knowledge service platform, providing various frequently asked questions knowledge bases and historical message backtracking services.

[0010] Preferably, the steps of authenticating the user identity through the account registration information and identifying the user permissions through the account information when the user logs in are as follows: when the user uses the system for the first time, fill in the basic information through the registration interface and select the user identity at the same time; after the user successfully registers, the account is bound to a specific role template based on the selected identity information; when the user logs in, the account name and password are entered to perform account verification. If the verification fails, the login is denied and an error message is prompted; if the verification is successful, the role type bound to the account is automatically retrieved and the corresponding permission configuration is identified; a login session is established, and the user ID, role information and permission range are written into the session status.

[0011] Preferably, the delivery matching index acquisition step is: merging the structured fields contained in the resume content into a natural language text to obtain a spliced ​​structured field, and converting the spliced ​​structured field into a standard resume text, and obtaining a job relevance coefficient based on the resume text evaluation; obtaining the language expression quality, content coverage comprehensiveness and information redundancy based on the resume text evaluation, and calculating the content adaptation coefficient based on the language expression quality, content coverage comprehensiveness and information redundancy; obtaining the latest update time of the resume and the current job posting time, calculating the absolute time difference between the latest update time and the current job posting time, and recording it as the time matching degree; obtaining the total number of historical submissions of the resume and the number of positive feedbacks obtained, and calculating the ratio of the number of positive feedbacks obtained to the total number of historical submissions to obtain the degree of positive feedback of the resume delivery; according to the time matching degree The positive impact coefficient of historical delivery is calculated based on the degree of positive feedback from resume delivery; the job relevance coefficient, content adaptation coefficient and historical delivery positive impact coefficient are normalized, and the delivery matching index is evaluated based on the normalized job relevance coefficient, content adaptation coefficient and historical delivery positive impact coefficient. The specific acquisition steps are: DM = a1×PR'+a2×CA'+a3×HD'; where DM is the delivery matching index, PR' is the normalized job relevance coefficient, CA' is the normalized content adaptation coefficient, HD' is the normalized historical delivery positive impact coefficient, and a1, a2 and a3 are the weight coefficients of the normalized job relevance coefficient, the weight coefficient of the normalized content adaptation coefficient and the weight coefficient of the normalized historical delivery positive impact coefficient.

[0012] Preferably, the step of obtaining the job relevance coefficient is: obtaining the job description of the deliverable job, extracting key terms, skill words and job descriptions from the job description as a job keyword set by the TF-IDF method, and obtaining the total number of job keywords in the job keyword set; counting the number of job keywords appearing in the resume text, recording it as the number of resume keywords, and calculating the ratio of the number of resume keywords to the total number of job keywords to obtain the keyword matching rate; identifying keywords related to project experience in the resume text from the job description, recording them as project keywords, and constructing a project keyword set based on the project keywords to obtain the total number of project keywords in the project keyword set; identifying the actual number of project keywords that appear in the project experience part of the resume text, recording it as the actual number of project keywords, and calculating the ratio of the actual number of project keywords to the total number of project keywords to obtain the project matching rate; and calculating the job relevance coefficient based on the keyword matching rate and the project matching rate.

[0013] Preferably, the steps of extracting key terms, skill words and job descriptions from the job description as a job keyword set by the TF-IDF method are as follows: cleaning and segmenting the job description text, the cleaning and segmentation processing including removing punctuation, meaningless symbols and stop words; counting the frequency of each word in each job description, calculating the proportion of the word in the current document, recorded as the word frequency; counting the number of documents in which the word appears in all job descriptions, and calculating the inverse document frequency of the word; for each word, calculating the product of the frequency and the inverse document frequency to obtain the TF-IDF value; setting an effective number, selecting the word with the highest TF-IDF value corresponding to the effective number in each job description, and extracting it as the keyword set for the position.

[0014] Preferably, the steps for obtaining the content adaptation coefficient are as follows: obtaining the language expression quality through resume text evaluation; obtaining the total number of modules constituting the resume and the number of modules filled in the resume, and calculating the ratio of the number of modules filled in the resume to the total number of modules constituting the resume to obtain the comprehensiveness of content coverage; performing word segmentation on the resume text, removing stop words that have no actual semantic contribution, counting the number of occurrences of all valid words, and constructing a word frequency table, setting a high-frequency threshold, screening out words greater than the high-frequency threshold from the word frequency table, recording them as high-frequency words, summing up the total number of occurrences of all high-frequency words to obtain the cumulative number of redundant words, and calculating the ratio of the cumulative number of redundant words to the number of occurrences of all valid words to obtain the degree of information redundancy; normalizing the language expression quality, content coverage comprehensiveness and information redundancy, and calculating the content adaptation coefficient based on the normalized language expression quality, content coverage comprehensiveness and information redundancy.

[0015] Preferably, the step of obtaining the language expression quality is: extracting all words from the resume text, counting the total number of words, identifying grammatical errors, spelling errors and punctuation errors through a grammar checking tool, counting the number of errors in the resume, and calculating the ratio of the number of errors to the total number of words to obtain language standardization; obtaining readability parameters from the resume text, the readability parameters include the total number of words, the total number of sentences and the average number of letters per word, and calculating the content readability using the Flesh reading ease score method based on the readability parameters; normalizing the language standardization and content readability, and calculating the language expression quality based on the normalized language standardization and content readability.

[0016] Preferably, the step of screening out the resume most suitable for delivery according to the delivery matching index is: obtaining the delivery matching index of all resumes in the resume database, sorting all resumes from high to low according to the delivery matching index, and selecting the resume with the highest delivery matching index as the resume most suitable for delivery.

[0017] Preferably, the intelligent educational resource management method based on the cloud platform includes the following steps: Step 1: When registering an account, the user identity is authenticated through the account registration information, and the user authority is identified through the account information when the user logs in. The user identity includes supporting teachers, students and enterprises; Step 2: After the user authority is identified, the teacher creates courses, uploads courseware, organizes chapter structures, and associates resources such as micro-videos and chapter tests according to the authority; students access learning resources according to the authority; Step 3: Each time a student accesses a learning resource, the learning completion status data is recorded, and the learning completion status data includes video viewing records, chapter test completion status, and Step 4: Provide a resume editing interface, students can edit their resumes through the resume editing interface, and can directly upload learning completion data in the resume, and store each edited resume in the resume database; teachers screen out available positions, and for each available position, obtain each version of resume data. The resume data includes resume content, update time point, and historical delivery records. The delivery matching index is obtained based on the resume data evaluation, and the most suitable resume is screened based on the delivery matching index and delivered; Step 5: Push corresponding reminders based on user account identity; Step 6: Build a knowledge service platform, provide various frequently asked questions knowledge bases and historical message backtracking services.

[0018] Technical effects and advantages of the present invention:

[0019] Every time a student visits a learning resource, data on learning completion is recorded. Students edit their resumes through the resume editing interface and can directly upload learning completion data in their resumes. Each edited resume is stored in the resume database. Teachers select available positions and obtain data on each version of the resume for each available position. The resume data includes resume content, update time, and historical submission records. The submission matching index is obtained based on the resume data evaluation. The most suitable resume is selected based on the submission matching index and submitted, effectively improving the matching degree between the resume and the position and increasing the student's interview success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a structural diagram of the cloud-based intelligent educational resource management system provided in the embodiment of the present application.

[0021] Figure 2 Flowchart of the cloud-based intelligent educational resource management method provided in the embodiment of this application. DETAILED DESCRIPTION

[0022] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely examples. The cloud platform-based intelligent educational resource management system and method involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] The present invention provides an intelligent education resource management system based on a cloud platform, such as Figure 1 As shown, the system includes:

[0024] The user and permission management module is used to authenticate user identities through account registration information during account registration, and to identify user permissions through account information during user login. User identities include teachers, students, enterprises, and other categories of users, laying the identity foundation for the operation of the course and learning resource management module;

[0025] In this embodiment, it should be specifically explained that the steps of authenticating the user identity through the account registration information and identifying the user rights through the account information when the user logs in are as follows:

[0026] When a user uses the system for the first time, they need to fill in basic information on the registration interface. Basic information includes user name, password, mobile phone number / email address, etc., and select or fill in the user identity (such as "teacher", "student", "corporate HR", etc.);

[0027] After a user successfully registers, the system binds their account to a specific role template (such as a student template or a teacher template) based on the selected identity information. An administrator preliminary review mechanism can also be set up. For example, teachers need to submit their work ID for verification, and corporate users need to upload three certificates to complete identity authenticity verification.

[0028] When a user logs in, they enter their account name, password (and verification code). The system first verifies the account to confirm whether the user exists and whether the password matches. If the verification fails, the login is rejected and an error message is displayed.

[0029] When the account is successfully verified, the role type bound to the account will be automatically retrieved to identify its corresponding permission configuration, such as students can access the course learning module, teachers can access the course management and marking modules, etc.

[0030] The system establishes a login session and writes the user ID, role information, and permission range into the session state, which serves as the basis for subsequent function access. Each time a user requests access to a function, the system verifies whether they are authorized to access it through the permission table, thereby achieving role-based function isolation and access control.

[0031] The course and learning resource management module is used to identify user permissions. Teachers can then create courses, upload courseware, organize chapter structures, create micro-videos, and associate chapter tests with other resources based on their permissions. Students can access learning resources based on their permissions, including entering the course learning page, viewing recommended courses, and adding learning content to their favorites.

[0032] This module enables teachers to structure course content and manage resources, as well as students to access and use learning resources in a personalized manner. The benefit of this module lies in the construction of a unified, efficient, and scalable teaching content management system, enabling teachers to flexibly organize teaching resources and promote the continuous optimization of course content. It also enables students to easily access, manage, and review learning materials, improving the systematic and coherent nature of course learning, and further promoting the efficient use of teaching resources and enhanced learning outcomes.

[0033] The learning process and assessment module is used to record each student's access to learning resources and obtain learning completion data, including video viewing records, chapter test completion status, homework submission status, and course progress completion rate;

[0034] By recording every student's access to learning resources, we systematically generate multi-dimensional learning completion data, including video viewing, chapter tests, homework submissions, and course progress, providing teachers with accurate teaching feedback. This module's benefit lies in its comprehensive reflection of students' learning process and mastery, helping teachers promptly identify weaknesses and provide personalized guidance. It also encourages students to self-monitor their learning progress, improving learning initiative and course completion rates, and providing reliable data support for subsequent evaluation, recommendations, and competency modeling.

[0035] The employment and enterprise docking module is used to provide a resume editing interface. Students can edit their resumes through the resume editing interface and directly upload their learning completion data in the resume. Each edited resume is stored in the resume database.

[0036] Teachers screen out available positions. For each available position, they obtain resume data for each version, including resume content, update time, and historical submission records. Based on the resume data, they evaluate the resume data to obtain a submission matching index. Based on the submission matching index, they screen out the most suitable resumes and submit them.

[0037] In this embodiment, it should be specifically explained that the steps for obtaining the delivery matching index are:

[0038] Merge the structured fields contained in the resume into a natural language text to obtain concatenated structured fields, such as education background, project experience, skill list, and job intentions. Convert the concatenated structured fields into a standard resume text and evaluate the resume text to obtain the job relevance coefficient.

[0039] The language quality, content comprehensiveness, and information redundancy of the resume text are evaluated, and the content adaptation coefficient is calculated based on the language quality, content comprehensiveness, and information redundancy.

[0040] Get the latest update time of the resume and the current job posting time, calculate the absolute time difference between the latest update time and the current job posting time, and record it as the time matching degree. The closer the resume update time is to the job posting time, the more likely the update is a targeted optimization for the position, and the higher the matching degree;

[0041] Obtain the total number of resume submissions and the number of positive feedback received. Positive feedback includes interview invitations, internship offers, and formal offers. Calculate the ratio of the number of positive feedback received to the total number of historical submissions to determine the degree of positive feedback on the resume submission. The more positive feedback, the more adaptable the resume version is to the job market.

[0042] The positive impact coefficient of historical delivery is calculated based on the time matching degree and the positive feedback degree of resume delivery. The specific steps to obtain it are:

[0043]

[0044] In the formula, HD represents the positive impact coefficient of historical delivery, tm represents the degree of time matching, and pf represents the degree of positive feedback of resume delivery. This avoids extreme interference in the results when one dimension is extremely high but the other is extremely low. By processing the square root, the fluctuation range of the product value can be compressed.

[0045] Normalize the job correlation coefficient, content adaptation coefficient, and historical delivery positive impact coefficient. Then evaluate the delivery matching index based on the normalized job correlation coefficient, content adaptation coefficient, and historical delivery positive impact coefficient. The specific steps for obtaining the index are as follows:

[0046] DM=a1×PR'+a2×CA'+a3×HD';

[0047] In the formula, DM represents the delivery match index, and PR' represents the normalized job relevance coefficient. The higher the job relevance coefficient, the more closely the resume matches the job in terms of skill keywords, job responsibilities, and professional background. Therefore, the system will assign a higher delivery match index to the resume and recommend this version for job applications. CA' represents the normalized content adaptability coefficient. When a resume has a clear logical structure, complete module divisions, and uses professional and accurate language, it not only improves the recruiter's reading efficiency but also makes it easier to highlight the applicant's comprehensive qualities and professional abilities. Conversely, even if the resume's professional background matches the job, problems such as redundant information, confusing expression, and messy formatting may result in a low evaluation or even be ignored. Therefore, the higher the content adaptation coefficient, the more the resume's presentation conforms to the expression specifications of a standard professional resume, and the easier it is to stand out among many resumes, thereby directly improving its delivery matching index in the system. HD' is expressed as the normalized historical delivery positive impact coefficient. The positive performance of a resume in history can serve as an external verification of its job suitability, and therefore has important reference significance. The higher the coefficient, the more market-proven that resume version has been used for similar job applications. The system prioritizes such versions with positive feedback when recommending resumes for the current position, thereby improving the overall hit rate and submission success rate. a1, a2, and a3 represent the weight coefficients of the normalized job relevance coefficient, the normalized content adaptability coefficient, and the normalized historical submission positive impact coefficient, with a1 + a2 + a3 = 1. a1, a2, and a3 are derived using the Analytic Hierarchy Process (AHP), a mathematical method for multi-factor decision-making. It primarily constructs a multi-level structural model, decomposing complex decision problems into a goal layer, a criterion layer, and a scenario layer. Factors are then compared and scored pairwise to form a judgment matrix. The relative weights of each evaluation indicator are determined by calculating eigenvectors and performing consistency checks. This method transforms subjective judgments into quantitative weights, which can be used to comprehensively rank the impact of multiple evaluation factors.

[0048] In this embodiment, it should be specifically explained that the steps for obtaining the position correlation coefficient are:

[0049] Obtain job descriptions of available positions, extract key terms, skill terms, and job descriptions from the job descriptions using the TF-IDF method as a set of job keywords, and obtain the total number of job keywords in the set.

[0050] Count the number of job keywords that appear in the resume text, record it as the number of resume keywords, and calculate the ratio of the number of resume keywords to the total number of job keywords to get the keyword matching rate;

[0051] Identify keywords related to project experience in the resume from the job description and record them as project keywords, such as "lead", "develop", "optimization", "system design", etc., and construct a project keyword set based on the project keywords to obtain the total number of project keywords in the project keyword set;

[0052] In the project experience section of the resume text, identify the actual number of project keywords that appear, record it as the actual number of project keywords, and calculate the ratio of the actual number of project keywords to the total number of project keywords to obtain the project matching rate;

[0053] The job correlation coefficient is calculated based on the keyword matching rate and the project matching rate. The specific steps for obtaining it are:

[0054]

[0055] In the formula, PR represents the position correlation coefficient, KM represents the keyword matching rate, and PM represents the project matching rate.

[0056] The TF-IDF method is a commonly used text mining algorithm used to measure the importance of a term within a set of documents. It combines two factors: term frequency (TF) and inverse document frequency (IDF). TF indicates how often a term appears in a single document, reflecting its importance to that document; IDF measures the discriminative power of a term within the entire document collection. If a term appears in a large number of documents, its importance decreases. A higher TF-IDF value indicates that the term appears frequently in the current document and less frequently in other documents, making it more representative.

[0057] In this embodiment, it should be specifically explained that the steps of extracting key terms, skill words, and job descriptions from job descriptions using the TF-IDF method as a job keyword set are as follows:

[0058] Clean and segment the job description text. This includes removing punctuation, meaningless symbols, and stop words. The goal of preprocessing is to convert each document into a sequence of valid words to facilitate subsequent statistics.

[0059] Count the frequency of each word in each job description and calculate the proportion of the word in the current document, which is recorded as the word frequency. The word frequency reflects the degree of emphasis on the word in the current job description;

[0060] Count the number of documents where the word appears in all job descriptions and calculate the inverse document frequency of the word. The inverse document frequency reflects the "rarity" of the word in the entire corpus; the rarer the word, the more representative it is of a specific position.

[0061] For each word, calculate the product of the frequency and the inverse document frequency to obtain the TF-IDF value. The larger the TF-IDF value, the higher the frequency of the word in the current job description, the less common it is in other jobs, and the stronger its representativeness.

[0062] Set an effective number, select the words with the highest TF-IDF values corresponding to the effective number in each job description, and extract them as the keyword set for this job.

[0063] In this embodiment, it should be specifically noted that the steps for obtaining the content adaptation coefficient are as follows:

[0064] Obtain the language expression quality through resume text evaluation;

[0065] Obtain the total number of module components of the resume and the number of filled modules in the resume, calculate the ratio of the number of filled modules in the resume to the total number of module components of the resume to obtain the content coverage comprehensiveness;

[0066] Perform word segmentation on the resume text, remove stop words that have no actual semantic contribution, such as "of", "is", "and", etc., count the occurrence times of all effective words, and construct a word frequency table. Set a high-frequency threshold, screen out the words greater than the high-frequency threshold from the word frequency table, record them as high-frequency words, sum up the total occurrence times of all high-frequency words to obtain the cumulative number of redundant words. This value represents the proportion basis of redundant content in the resume. Calculate the ratio of the cumulative number of redundant words to the occurrence times of all effective words to obtain the information redundancy degree;

[0067] Perform normalization processing on the language expression quality, content coverage comprehensiveness, and information redundancy degree, and calculate the content adaptation coefficient based on the normalized language expression quality, content coverage comprehensiveness, and information redundancy degree. The specific acquisition steps are as follows:

[0068] CA = ln(1 + le'×cg')×(1 + ir' 2 );

[0069] In the formula, CA represents the content adaptation coefficient, le' represents the normalized language expression quality, cg' represents the normalized content coverage comprehensiveness. Multiply the language expression quality and the content coverage comprehensiveness as the basic score, and use the logarithmic function to achieve smooth non-linear compression to avoid the high value from overly amplifying the result. ir' represents the normalized information redundancy degree, and perform square penalty processing on the information redundancy degree so that the higher the redundancy degree, the greater the impact on the score. The formula can balance the evaluation of the language quality, structural integrity, and conciseness of the resume. The higher the score, the clearer, more comprehensive, and less redundant the content, which is suitable for job application. It can effectively suppress the problem of overly high scores caused by content duplication.

[0070] In this embodiment, it should be specifically explained that the steps for obtaining the language expression quality are:

[0071] Extract all words from the resume text, count the total number of words, and scan the resume content using a grammar checker, such as LanguageTool or Grammarly. Use the grammar checker to identify grammatical errors, spelling errors, and punctuation errors. Count the number of errors in the resume and calculate the ratio of the number of errors to the total number of words to determine the language standardization.

[0072] Obtain readability parameters from the resume text. Readability parameters include the total number of words, the total number of sentences, and the average number of letters per word. Calculate the readability of the content using the Flesh Reading Ease Score based on the readability parameters. The specific steps are as follows:

[0073]

[0074] In the formula, kd represents the readability of the content. The higher the value, the shorter and more popular the sentence is, and the more suitable it is for quick reading. W Expressed as the total number of words, num S Expressed as the total number of sentences, num L Expressed as the average number of letters per word;

[0075] Normalize the language standardization and content readability, and calculate the language expression quality based on the normalized language standardization and content readability. The specific acquisition steps are as follows:

[0076]

[0077] In the formula, le represents the quality of language expression, ls represents the language standardization, and kd represents the readability of the content. The formula is based on the logical function The core of the equation is to ensure that the score fluctuates smoothly within the interval [0, 1]. 2ls increases the weight of language standardization in the overall score, while ln(1+kd) is used to extract the incremental effect of readability in the early stages and mitigate its marginal impact. This formula comprehensively measures the impact of language standardization and readability on the quality of expression. The more standardized the language and the easier the content is to read, the higher the score. If the language is standardized but the sentences are obscure, or if the readability is high but the grammar is confusing, the score will be naturally suppressed, making the final score more closely reflect the actual level of language expression.

[0078] The Flesh Readability Scale is a classic formula for assessing text readability. It analyzes the average sentence length (number of words per sentence) and the average word length (measured in letters) in a text to calculate a score between 0 and 100 to measure the text's readability. A higher score indicates easier reading; a lower score indicates more complex content and a higher reading difficulty.

[0079] In this embodiment, it should be specifically explained that the steps for selecting the most suitable resumes for delivery according to the delivery matching index are as follows:

[0080] Obtain the delivery matching index of all resumes in the resume database, sort all resumes from high to low according to the delivery matching index, and select the resume with the highest delivery matching index as the most suitable resume for delivery.

[0081] The message and notification management module is used to push corresponding reminders based on user account identity, such as course updates, exam times, job recommendation notifications, etc.

[0082] By combining user account identity with course progress status, personalized reminder push notifications, such as course update notifications, upcoming exam times, and job recommendations, effectively enhance the system's interactivity and timeliness. This module helps students stay informed of key learning milestones and job opportunities, avoiding missing out on important matters due to information lags. It also provides precise communication channels for teachers and administrators, improving the platform's overall operational efficiency and user engagement, and ensuring the orderly progress of teaching and service processes.

[0083] The knowledge support module is used to build a knowledge service platform, providing various frequently asked questions knowledge bases and historical message backtracking services so that students can obtain experience answers through the knowledge service platform when they encounter problems in the process of learning or employment, and improve their self-service problem-solving capabilities.

[0084] By building a FAQ knowledge base and a historical message backtracking mechanism, we provide students with efficient and continuous self-service support during their studies, job search, and other processes. This significantly reduces reliance on manual consultation and improves the speed and accuracy of problem-solving. The introduction of this module not only enhances the platform's service intelligence but also helps students quickly access authoritative and structured information when they encounter operational confusion, policy questions, or process bottlenecks. This enhances their ability to independently resolve issues, thereby optimizing the overall user experience and reducing the burden of answering questions for teachers and administrators.

[0085] In this embodiment, it is necessary to specifically explain that the intelligent educational resource management method based on the cloud platform, such as Figure 2 As shown, the following steps are included:

[0086] Step 1: When registering an account, the user's identity is authenticated through the account registration information, and the user's permissions are identified through the account information when the user logs in. User identities include teachers, students, and enterprises.

[0087] Step 2: After identifying user permissions, teachers create courses, upload courseware, organize chapter structures, associate micro-videos with chapter tests, and other resources based on their permissions; students access learning resources based on their permissions.

[0088] Step 3: Record each student's access to learning resources to obtain learning completion data, including video viewing records, chapter test completion status, homework submission status, and course progress;

[0089] Step 4: Provide a resume editing interface, through which students can edit their resumes and upload their learning completion data directly in their resumes. Each edited resume will be stored in the resume database;

[0090] Teachers screen out available positions. For each available position, they obtain resume data for each version, including resume content, update time, and historical submission records. Based on the resume data, they evaluate the resume data to obtain a submission matching index. Based on the submission matching index, they screen out the most suitable resumes and submit them.

[0091] Step 5: Push corresponding reminders based on user account identity;

[0092] Step 6: Build a knowledge service platform to provide various frequently asked questions knowledge bases and historical message backtracking services.

[0093] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0094] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An intelligent educational resource management system based on a cloud platform, characterized by: The system comprises: The user and authority management module is used to authenticate the user's identity through the account registration information when registering an account, and to identify the user's authority through the account information when the user logs in. The user identities include teachers, students and enterprises; The course and learning resource management module is used to identify user permissions, allowing teachers to create courses, upload courseware, organize chapter structures, and associate micro-videos and chapter tests based on permissions; students can access learning resources based on permissions; The learning process and evaluation module records each student's access to learning resources and obtains learning completion data; The employment and enterprise docking module is used to provide a resume editing interface. Students can edit their resumes through the resume editing interface and directly upload their learning completion data in the resume. Each edited resume is stored in the resume database. Teachers screen out available positions. For each available position, they obtain resume data for each version, including resume content, update time, and historical submission records. Based on the resume data, they evaluate the resume data to obtain a submission matching index. Based on the submission matching index, they screen out the most suitable resumes and submit them. Message and notification management module, used to push corresponding reminders based on user account identity; The knowledge support module is used to build a knowledge service platform, providing various frequently asked questions knowledge bases and historical message backtracking services.

2. The cloud-based intelligent educational resource management system according to claim 1, characterized in that: The steps of authenticating the user identity through the account registration information and identifying the user rights through the account information when the user logs in are as follows: When a user uses the system for the first time, he / she fills in basic information through the registration interface and selects the user identity; After the user successfully registers, the account is bound to a specific role template based on the selected identity information; When logging in, the user enters the account name and password for account verification. If the verification fails, the login is denied and an error message is prompted; If the verification is successful, the role type bound to the account is automatically retrieved and the corresponding permission configuration is identified; Establish a login session and write the user ID, role information, and permission range to the session state.

3. The cloud-based intelligent educational resource management system according to claim 1, characterized in that: The steps for obtaining the delivery matching index are: Merge the structured fields contained in the resume content into a natural language text to obtain a spliced ​​structured field, convert the spliced ​​structured field into a standard resume text, and evaluate the resume text to obtain a job relevance coefficient; The language quality, content comprehensiveness, and information redundancy of the resume text are evaluated, and the content adaptation coefficient is calculated based on the language quality, content comprehensiveness, and information redundancy. Get the latest update time of the resume and the current job posting time, calculate the absolute time difference between the latest update time and the current job posting time, and record it as the time matching degree; Obtain the total number of resume submissions and the number of positive feedbacks received, and calculate the ratio of the number of positive feedbacks received to the total number of historical submissions to obtain the degree of positive feedback on the resume submission; The positive impact coefficient of historical delivery is calculated based on the degree of time matching and the degree of positive feedback from resume delivery; Normalize the job correlation coefficient, content adaptation coefficient, and historical delivery positive impact coefficient. Then evaluate the delivery matching index based on the normalized job correlation coefficient, content adaptation coefficient, and historical delivery positive impact coefficient. The specific steps for obtaining the index are as follows: DM=a1×PR'+a2×CA'+a3×HD'; In the formula, DM represents the delivery matching index, PR' represents the normalized job correlation coefficient, CA' represents the normalized content adaptation coefficient, HD' represents the normalized historical delivery positive impact coefficient, a1, a2, and a3 represent the weight coefficients of the normalized job correlation coefficient, the weight coefficient of the normalized content adaptation coefficient, and the weight coefficient of the normalized historical delivery positive impact coefficient.

4. The cloud-based intelligent educational resource management system according to claim 3, characterized in that: The steps for obtaining the position correlation coefficient are: Obtain job descriptions of available positions, extract key terms, skill terms, and job descriptions from the job descriptions using the TF-IDF method as a set of job keywords, and obtain the total number of job keywords in the set. Count the number of job keywords that appear in the resume text, record it as the number of resume keywords, and calculate the ratio of the number of resume keywords to the total number of job keywords to get the keyword matching rate; Identify keywords related to project experience in the resume text from the job description, record them as project keywords, build a project keyword set based on the project keywords, and obtain the total number of project keywords in the project keyword set; In the project experience section of the resume text, identify the actual number of project keywords that appear, record it as the actual number of project keywords, and calculate the ratio of the actual number of project keywords to the total number of project keywords to obtain the project matching rate; The job correlation coefficient is calculated based on the keyword matching rate and the project matching rate.

5. The cloud-based intelligent educational resource management system according to claim 4, characterized in that: The steps of extracting key terms, skill words and job descriptions from job descriptions using the TF-IDF method as a job keyword set are as follows: Clean and segment the job description text, which includes removing punctuation, meaningless symbols, and stop words; Count the frequency of each word in each job description and calculate the proportion of the word in the current document, which is recorded as the word frequency; Count the number of documents in which the word appears in all job descriptions and calculate the inverse document frequency of the word; For each word, calculate the product of frequency and inverse document frequency to get the TF-IDF value; Set an effective number, select the words with the highest TF-IDF value corresponding to the effective number in each job description, and extract them as the keyword set for the position.

6. The cloud-based intelligent educational resource management system according to claim 3, characterized in that: The steps for obtaining the content adaptation coefficient are: The quality of language expression is obtained through resume text evaluation; Obtain the total number of modules in the resume and the number of completed modules in the resume, and calculate the ratio of the number of completed modules in the resume to the total number of modules in the resume to obtain the comprehensiveness of content coverage; The resume text is segmented, stop words with no actual semantic contribution are removed, the occurrences of all valid words are counted, and a word frequency table is constructed. A high-frequency threshold is set, and words with a frequency greater than the high-frequency threshold are filtered out from the word frequency table and recorded as high-frequency words. The total occurrence of all high-frequency words is summed up to obtain the cumulative number of redundant words. The cumulative number of redundant words is then compared with the occurrence of all valid words to obtain the degree of information redundancy. The language expression quality, content coverage comprehensiveness and information redundancy are normalized, and the content adaptation coefficient is calculated based on the normalized language expression quality, content coverage comprehensiveness and information redundancy.

7. The cloud-based intelligent educational resource management system according to claim 6, characterized in that: The steps for obtaining the language expression quality are: Extract all words from the resume text, count the total number of words, use grammar checking tools to identify grammatical errors, spelling errors, and punctuation errors, count the number of errors in the resume, and calculate the ratio of the number of errors to the total number of words to obtain language standardization; Obtain readability parameters from the resume text, including the total number of words, the total number of sentences, and the average number of letters per word. Calculate the content readability using the Flesh Reading Ease Score based on the readability parameters. The language standardization and content readability are normalized, and the language expression quality is calculated based on the normalized language standardization and content readability.

8. The cloud-based intelligent educational resource management system according to claim 5, characterized in that: The steps for selecting the most suitable resumes for delivery based on the delivery matching index are as follows: Obtain the delivery matching index of all resumes in the resume database, sort all resumes from high to low according to the delivery matching index, and select the resume with the highest delivery matching index as the most suitable resume for delivery.

9. A cloud-based intelligent educational resource management method, for implementing the cloud-based intelligent educational resource management system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: When registering an account, the user's identity is authenticated through the account registration information, and the user's permissions are identified through the account information when the user logs in. User identities include teachers, students, and enterprises. Step 2: After identifying user permissions, teachers create courses, upload courseware, organize chapter structures, associate micro-videos with chapter tests, and other resources based on their permissions; students access learning resources based on their permissions. Step 3: Record each student's access to learning resources to obtain learning completion data, which includes video viewing records, chapter test completion status, homework submission status, and course progress; Step 4: Provide a resume editing interface, through which students can edit their resumes and upload their learning completion data directly in their resumes. Each edited resume will be stored in the resume database; Teachers screen out available positions. For each available position, they obtain resume data for each version, including resume content, update time, and historical submission records. Based on the resume data, they evaluate the resume data to obtain a submission matching index. Based on the submission matching index, they screen out the most suitable resumes and submit them. Step 5: Push corresponding reminders based on user account identity; Step 6: Build a knowledge service platform to provide various frequently asked questions knowledge bases and historical message backtracking services.

Images