Career guidance teaching resource ai generation system

Abstract

The application discloses an employment guidance teaching resource AI generation system and relates to the technical field of artificial intelligence, comprising the following steps: collecting target post demand description files, successful employment user ability evolution data and student current ability data, constructing a standardized post ability vector and an ability evolution path atlas, extracting a student ability vector, extracting an ability difference label set according to the student ability vector and the standardized post ability vector, matching or generating a teaching resource unit according to the ability difference label set, and obtaining a teaching resource unit pushing sequence according to the ability evolution path atlas, the student ability vector and the standardized post ability vector; the system has the beneficial effects that the differences between student ability and post demand can be dynamically analyzed, and personalized teaching resources can be matched, the problems of insufficient resource matching precision and missing ability evaluation in traditional employment guidance can be solved, and the pertinence and timeliness of employment guidance can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence technology, and particularly relates to an AI generation system for employment guidance teaching resources. BACKGROUND

[0002] University student employment guidance is an important part of the university education system, which refers to helping students to clarify the career direction and improve the employment competitiveness through professional and systematic services, and finally realize the smooth transition from campus to workplace.

[0003] At present, the universities mainly rely on general course arrangement, experience type lecture and artificial consultation in the process of carrying out employment guidance. Students usually choose jobs and learning paths according to their own interests or vague professional direction, and lack of precise guidance for specific job ability requirements, which leads to that students often cannot accurately identify the gap between their own ability and job requirements when facing specific professional positions, and it is also difficult to obtain teaching resources with clear guidance, resulting in the dislocation between ability training and employment goals.

[0004] Therefore, an AI generation system for employment guidance teaching resources is proposed. SUMMARY

[0005] In view of the above prior art situation, the present application is proposed. The embodiments of the present application provide an AI generation system for employment guidance teaching resources, which can dynamically identify the difference between student ability and job requirements, accurately match personalized teaching resources, and improve the pertinence and timeliness of employment guidance.

[0006] According to an aspect of the present application, an employment guidance teaching resource AI generation system is provided, comprising: a data acquisition module for acquiring a requirement description file of a target post, capability evolution data of a user successfully employed in the target post, and current capability data of a student to be guided; a post capability analysis module for extracting a set of post capability tags based on the target post description file and mapping the set of post capability tags into a standardized post capability vector; a success path modeling module for constructing a capability evolution path graph based on the capability evolution data, the capability evolution path graph comprising a plurality of time sequence nodes and corresponding node capability vectors; a student capability portrait generation module for extracting a student capability vector corresponding to the structure of the standardized post capability vector from the current capability data of the student to be guided; a capability difference analysis module for mapping dimension items in the student capability vector and the standardized post capability vector that exceed a preset threshold to a set of capability difference tags; a resource matching and generation module for matching teaching resource units containing learning materials and evaluation materials from a teaching resource database according to the set of capability difference tags, and generating new teaching resource units based on the set of capability difference tags if no successful matching is made; a path matching and pushing module for performing similarity matching of the student capability vector and the standardized post capability vector with node capability vectors in the capability evolution path graph respectively, determining a current capability node and a target capability node, and determining a pushing order of the teaching resource units according to the node order between the current capability node and the target capability node; and a resource recommendation module for pushing the teaching resource units to a student terminal device in the pushing order.

[0007] According to another aspect of the present application, an employment guidance teaching resource AI generation method is provided, comprising: collecting a demand description file of a target post, capability evolution data of a plurality of users who successfully entered the target post, and current capability data of a student to be guided; extracting a post capability tag set based on the target post description file, and mapping the post capability tag set to a standardized post capability vector; constructing a capability evolution path graph based on the capability evolution data, the capability evolution path graph comprising a plurality of time sequence nodes and corresponding node capability vectors; extracting a student capability vector corresponding to the structure of the standardized post capability vector according to the current capability data of the student to be guided; mapping the dimension items in the student capability vector and the standardized post capability vector that exceed a preset threshold to a capability difference tag set; matching a teaching resource unit containing learning materials and evaluation materials from a teaching resource database according to the capability difference tag set, and if the matching is unsuccessful, generating a new teaching resource unit based on the capability difference tag; performing similarity matching of the student capability vector and the standardized post capability vector with the node capability vectors in the capability evolution path graph respectively to determine a current capability node and a target capability node, and determining a push order of the teaching resource unit according to the node order between the current capability node and the target capability node; and pushing the teaching resource unit to a student terminal device according to the push order.

[0008] Compared with the prior art, the employment guidance teaching resource AI generation system according to the embodiments of the present application can dynamically analyze the difference between the student's capability and the post demand and match personalized teaching resources, solve the problems of insufficient resource matching accuracy and missing capability evaluation in traditional employment guidance, and thus improve the pertinence and timeliness of employment guidance. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application taken in conjunction with the accompanying drawings. The drawings provided in the present application are used to provide further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0010] FIG. 1 The framework diagram of the employment guidance teaching resource AI generation system of the present application.

[0011] FIG. 2 The timing diagram of the employment guidance teaching resource AI generation system of the present application.

[0012] FIG. 3 The flowchart of the employment guidance teaching resource AI generation method of the present application. DETAILED DESCRIPTION

[0013] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0014] SUMMARY

[0015] At present, in colleges and universities or vocational training institutions, although information-based employment guidance services have been initially developed, such as providing career-related recommendations to students through intelligent question and answer systems, career assessment tools or online learning platforms, etc., these methods generally have the following problems:

[0016] 1) The job capacity requirements cannot be structured modeled, resulting in a lack of job-specific and capacity-oriented employment guidance content.

[0017] 2) Most existing learning path recommendation systems rely on course tags or popular learning behaviors, lack experience modeling based on "successful employment paths", and are difficult to provide effective growth guidance.

[0018] 3) Teaching resource recommendations are often based on static rules or course similarity matching, and cannot dynamically complete and automatically generate for students' capacity gaps, and cannot meet the customized, real-time, and systematic capacity improvement needs.

[0019] To address the above problems, the idea of the present application is to take "job capacity" as the core modeling object, and establish a full-process capacity-driven mechanism from job capacity analysis, student capacity portrait generation, capacity difference identification, resource generation and path recommendation.

[0020] Specifically, the present application analyzes the job description through natural language processing and semantic embedding model, extracts standardized job capacity tags and generates vector expression; combined with the capacity evolution data of successful job seekers, a capacity growth path atlas is constructed to realize the structured expression of typical capacity progression routes; on the student side, the current capacity data is extracted and a student capacity vector consistent with the job capacity dimension is generated; through vector difference and evolution path node distance analysis, the matching degree and gap between the student's current capacity state and the target job are identified; on this basis, a pre-trained teaching resource generation model and a knowledge graph reasoning mechanism are used to automatically generate personalized and target-oriented teaching resource units, and combined with the evolution order of the nodes in the capacity evolution path, the push path of the teaching resources is determined, finally realizing an employment guidance teaching resource AI generation system that is specific to a specific job, dynamically adapts to capacity changes, and supports intelligent content generation and push.

[0021] Exemplary System

[0022] FIG. 1~FIG. 2 An employment guidance teaching resource AI generation system according to an embodiment of the present application is illustrated, comprising a data collection module, a post ability analysis module, a success path modeling module, a student ability portrait generation module, an ability difference analysis module, a resource matching and generation module, a path matching and pushing module, and a resource recommendation module.

[0023] The data collection module is configured to collect a demand description file of a target post, ability evolution data of a user successfully employed in the target post, and current ability data of a student to be guided. The post ability analysis module is configured to extract a post ability tag set based on the target post description file, and map the post ability tag set to a standardized post ability vector. The success path modeling module is configured to construct an ability evolution path graph based on the ability evolution data, the ability evolution path graph comprising a plurality of time sequence nodes and corresponding node ability vectors. The student ability portrait generation module is configured to extract a student ability vector corresponding to the structure of the standardized post ability vector from the current ability data of the student to be guided. The ability difference analysis module is configured to map dimension items in the student ability vector and the standardized post ability vector that exceed a preset threshold to an ability difference tag set. The resource matching and generation module is configured to match a teaching resource unit comprising learning materials and evaluation materials from a teaching resource database according to the ability difference tag set, and generate a new teaching resource unit based on the ability difference tags if no successful matching is made. The path matching and pushing module is configured to perform similarity matching of the student ability vector and the standardized post ability vector with node ability vectors in the ability evolution path graph, respectively, to determine a current ability node and a target ability node, and determine a pushing order of the teaching resource unit according to a node order between the current ability node and the target ability node. The resource recommendation module is configured to push the teaching resource unit to a student terminal device according to the pushing order.

[0024] Specifically, the system first integrates post demand and historical success case data to establish a standardized ability evaluation system, then accurately locates the ability dimension that needs to be improved by comparing the quantitative difference between the current ability of a student and the requirements of a target post, and matches existing teaching resources according to the ability dimension that needs to be improved by the student. When existing teaching resources cannot meet the requirements, new teaching units containing knowledge point explanation and practical tasks are automatically generated, and the ability development path of a successful person is referred to to plan a learning order that conforms to the cognitive law for a student, so as to ensure that the ability improvement process and the career development goal are kept in synchronization.

[0025] Through the above technical solution, this application can detect the difference between students' abilities and target positions in real time, automatically generate targeted teaching resources and plan the optimal learning path. This technical solution solves the problems of low accuracy of resource matching and lack of scientific basis for learning paths in traditional employment guidance, and improves the fit between students' ability cultivation and career development needs.

[0026] This application further proposes a method for extracting a set of job competency tags based on a target job description document, which includes: performing word segmentation and entity recognition processing on the target job description document to obtain competency text fragments related to job requirements; and classifying and clustering the competency text fragments according to a pre-set competency classification lexicon and a contextual semantic model to obtain a set of job competency tags.

[0027] in:

[0028] Word segmentation and entity recognition processing refers to splitting the natural language text in the target job description file into lexical units with independent semantics and identifying entity names related to job capabilities. Specifically, it can be implemented using natural language processing tools such as the jieba word segmenter or the spaCy framework to extract key capability elements from unstructured job descriptions.

[0029] A competency classification thesaurus refers to a pre-established structured thesaurus containing industry-standard competency names and their classification relationships. Specifically, it can be constructed using a standard occupational classification system or an industry competency framework to provide standardized classification criteria for text fragments.

[0030] Contextual semantic models are machine learning models that can understand the semantic relationships of words in a specific context. Specifically, they can be implemented using pre-trained language models such as BERT or RoBERTa, and are used to identify the implicit ability requirement relationships in text fragments.

[0031] Classification clustering refers to grouping text fragments with the same ability attributes based on semantic similarity. Specifically, it can be implemented using K-means clustering algorithm or hierarchical clustering algorithm to eliminate redundant descriptions and generate a standardized set of ability labels.

[0032] Specifically:

[0033] First, when the system receives the target job description file, it breaks down the file content into independent word units through word segmentation. For example, "proficient in Python programming" is broken down into words such as "proficient", "master", "Python", and "programming".

[0034] Then, identify entities related to the ability, such as identifying "Python programming" as a technical ability entity;

[0035] Next, the extracted ability text fragments are input into the contextual semantic model and combined with standard terms in the ability classification lexicon. For example, "Python programming" is mapped to the "Python development skills" label under the "programming language ability" category.

[0036] Finally, clustering algorithms are used to merge semantically similar segments. For example, "proficient in data analysis tools" and "skilled in using Excel for data modeling" are clustered into the "data analysis ability" tag, thereby generating a structured set of job ability tags.

[0037] The above technical solution enables the system to identify and categorize commonalities in job description documents with differentiated expressions, thereby providing a unified benchmark for subsequent competency vector construction and ensuring the accuracy of teaching resource matching.

[0038] This application further proposes mapping a set of job competency tags to a standardized job competency vector, including: encoding the set of job competency tags into vectors using a preset semantic embedding algorithm; and normalizing and aligning the vector encoding results with dimensions according to a preset job competency dimension structure to obtain a standardized job competency vector.

[0039] in:

[0040] Preset semantic embedding algorithms refer to natural language processing techniques that convert text tags into numerical vectors. Specifically, they can be implemented using word embedding models or sentence embedding models. For example, the semantic information of job competency tags can be converted into numerical representations in a high-dimensional vector space using Word2Vec, BERT, or similar algorithms.

[0041] A pre-defined job competency dimension structure refers to a pre-defined standardized competency indicator system. This can be achieved using an industry-standard competency framework or job competency model. For example, competency can be divided into fixed dimensions such as professional skills, communication skills, and project management skills to ensure that the competency vectors of different positions or students are comparable.

[0042] Through the above technical solution, this application can transform unstructured job competency tags into standardized vectors with unified dimensions and semantic structure, providing a reliable data foundation for subsequent analysis of student competency differences.

[0043] This application further proposes a capability evolution path graph based on capability evolution data, including: time-series labeling of capability evolution data and extraction of node capability vectors corresponding to time-series nodes; stage clustering of node capability vectors according to a preset state transition modeling algorithm to obtain multiple capability evolution paths; and construction of a capability evolution path graph containing node capability vectors and their directed edge relationships based on the time sequence and capability transformation relationship between capability evolution paths.

[0044] in:

[0045] Time-series labeling refers to marking the capability status at different points in time in capability evolution data in a time sequence. Specifically, it can be implemented by timestamp labeling or event interval labeling to determine the order in which capability changes occur.

[0046] A node capability vector is a vectorized representation of a user’s capability status at a specific point in time. Specifically, it can be implemented by encoding the capability description text using a semantic embedding algorithm, which is used to quantify the capability development trajectory.

[0047] State transition modeling algorithms refer to computational models used to identify stage changes in the process of capability evolution. Specifically, they can be implemented using hidden Markov models or dynamic time warping algorithms to discover key turning points in capability development.

[0048] Stage clustering refers to classifying nodes with similar capability change patterns into the same evolutionary path. Specifically, it can be implemented using hierarchical clustering or spectral clustering algorithms to form multiple typical capability development branches.

[0049] A capability evolution path map refers to a graph structure that displays the dynamic process of capability development. Specifically, it can be implemented using a directed graph data structure to visualize the relationships between different capability enhancement paths.

[0050] Specifically, when constructing a capability evolution path map, the historical capability data of users before they join their target positions is first divided into time series. For example, the monthly skills assessment report is used as an independent time series node. Each node is vectorized and transformed into a numerical representation containing dimensions such as professional skills and communication skills. Then, the capability change magnitude between adjacent nodes is analyzed through state transition modeling algorithms. When a significant leap in capability dimension is detected, it is marked as a stage boundary point. Based on these boundary points, the capability evolution process is divided into several development stages, and user data with the same stage division pattern are clustered into the same path. The final map not only contains the capability vectors of each node, but also uses directed edges to label the transformation relationship between different stages. For example, the edge from the primary skill node to the intermediate skill node represents the direction of capability improvement.

[0051] Through the above technical solution, this application can transform discrete ability development data into a structured path graph, so that the subsequent system can automatically generate a learning path plan that conforms to the ability development law based on the connection relationship of directed edges in the graph, thus avoiding the cognitive load problem caused by the accumulation of learning resources in traditional methods.

[0052] This application further proposes to extract student ability vectors corresponding to the standardized job competency vector structure, including: uniformly formatting the student's current competency data and extracting competency information fragments of text for the students to be guided; constructing competency feature mapping rules based on the set of job competency tags, and extracting features from the competency information fragments according to the feature mapping rules to obtain an initial student competency vector matching the job competency tags; and normalizing and reorganizing the dimensions of the initial student competency vector to obtain a student competency vector corresponding to the standardized job competency vector structure.

[0053] in:

[0054] Uniform formatting refers to converting student ability data from different sources or in different formats into a unified data structure. This can be achieved using data cleaning tools and standardized templates to eliminate the interference of data format differences on subsequent analysis.

[0055] The ability feature mapping rule refers to the correspondence between text features and vector dimensions established based on the set of job ability labels. Specifically, it can be implemented using keyword matching algorithms and semantic similarity models to ensure that student ability information fragments are accurately mapped to standardized dimensions.

[0056] Normalization refers to transforming capability characteristics with different dimensions or numerical ranges into a unified numerical range. Specifically, it can be achieved using maximum-minimum normalization or Z-score normalization algorithms to eliminate the magnitude differences between different capability dimensions.

[0057] Specifically, students' current ability data is first input into a data cleaning tool, which removes redundant information and extracts ability information fragments using standardized templates. Then, based on a pre-set set of job ability tags, a keyword matching algorithm is used to identify features related to job requirements from the ability information fragments. A semantic similarity model is then used to map these features to corresponding vector dimensions, generating an initial student ability vector. This vector is then processed by a normalization algorithm and restructured according to the dimensional structure of the standardized job ability vector. Finally, a student ability vector with a structure completely consistent with the job ability vector is generated. Thus, the analysis of the difference between student abilities and job requirements can be conducted under the same dimensional structure, avoiding ability assessment bias caused by inconsistent vector structures.

[0058] Through the above technical solution, this application solves the problem of ability assessment error caused by the inconsistency between student ability data and job ability vector structure, ensures the dimensional alignment and numerical comparability of ability difference analysis, and provides a structurally consistent data foundation for subsequent accurate matching of teaching resources.

[0059] This application further proposes dimensional reorganization, which includes: rearranging the dimensions of the normalized student ability vector and padding missing values ​​with zeros according to the dimensional structure of the standardized job ability vector, so as to obtain a student ability vector with the same number of dimensions and semantic structure as the standardized job ability vector.

[0060] in:

[0061] Dimensional rearrangement refers to rearranging the dimensions of a student's competency vector according to the dimensional order of a standardized job competency vector. This can be achieved using matrix transpose or index mapping algorithms to eliminate differences in dimensional order caused by different data sources.

[0062] Zero-padding refers to filling the missing dimension positions with zero values ​​when the student's ability vector is missing in the dimensional structure corresponding to the standardized job ability vector. Specifically, the missing dimension positions can be identified through a dimension alignment detection algorithm to maintain the consistency of the number of vector dimensions.

[0063] Specifically, when generating student ability vectors, since the ability data sources of different students may have differences in dimensional order or some dimensions may be missing, the dimensional rearrangement operation is used to force the dimensional order of the student ability vectors to be aligned with the dimensional structure defined by the standardized job ability vector. At the same time, the missing dimension items are filled by zero-padding operation, so as to ensure that the two vectors are numerically compared in the same dimensional space when analyzing ability differences in the future.

[0064] For example, when a standardized job competency vector includes three dimensions: programming ability, communication ability, and project management ability, if a student's competency data only includes two dimensions: programming ability and communication ability, then zeros should be added to the project management ability dimension.

[0065] Through the above technical solution, this application eliminates the dimensional structure difference between student ability vectors and job ability vectors, ensures the dimensional consistency of ability difference analysis, avoids ability assessment bias caused by dimensional misalignment or missing dimensions, and provides a reliable data foundation for subsequent accurate matching of teaching resources.

[0066] This application further proposes mapping dimension items in the difference between student ability vectors and standardized job ability vectors that exceed a preset threshold to a set of ability difference labels, including: calculating the difference between the standardized job ability vector and the student ability vector dimension by dimension to obtain an ability difference vector; selecting dimension items in the ability difference vector that exceed a preset threshold as ability deficiency dimensions; and generating an ability difference label set based on the mapping relationship between the ability deficiency dimensions and the set of job ability labels.

[0067] in:

[0068] The competency difference vector is a numerical vector formed by calculating the difference between the standardized job competency vector and the student competency vector dimension by dimension. Specifically, it can be implemented by vector subtraction and is used to quantify the actual gap between students in each competency dimension.

[0069] A capability difference tag set refers to the set formed by mapping capability deficiency dimensions to corresponding job capability tags. Specifically, it can be implemented using a tag mapping table, that is, by looking up a preset dimension-tag correspondence table and converting the numerical capability deficiency dimensions into interpretable text tags.

[0070] Specifically, when calculating the capability difference vector, the standardized job capability vector and the student capability vector are first aligned under the same dimensional structure, and then a numerical subtraction operation is performed on each dimension.

[0071] For example, if the standardized job competency vector has a value of 0.85 in the "data analysis competency" dimension, while the student competency vector has a value of 0.52 in the same dimension, the corresponding competency difference is 0.33. When the preset threshold is 0.3, this dimension is determined to be a competency deficiency dimension. Subsequently, by querying the pre-established mapping relationship between dimensions and job competency labels, such as mapping the "data analysis competency" dimension to the "Python data processing" label, a set of competency difference labels containing specific competency deficiencies is finally generated.

[0072] Through the above technical solution, this application can accurately identify students' specific deficiencies in the ability dimensions of specific positions and generate structured ability difference labels, providing a clear directional basis for subsequent matching of teaching resources.

[0073] This application further proposes the following steps for generating new teaching resource units: generating task objectives that match ability difference labels using a pre-trained teaching resource generation model; retrieving knowledge points, skill requirements, and assessment requirements related to the task objectives using a pre-set teaching knowledge graph to obtain a draft teaching resource structure including the basic framework and elements of teaching resources; generating teaching resource text content containing learning materials and assessment materials based on the draft teaching resource structure using a pre-set natural language generation model; and structurally encapsulating the teaching resource text content to obtain the teaching resource unit.

[0074] in:

[0075] Pre-trained teaching resource generation models refer to artificial intelligence models trained on a large amount of teaching resource data. Specifically, they can be implemented using generative models based on the Transformer architecture, which are used to automatically generate corresponding learning task objectives based on ability difference labels.

[0076] A pre-set teaching knowledge graph refers to a structured knowledge base that includes the relationships between knowledge points and skill levels. Specifically, it can be implemented using a knowledge network built on a graph database, which is used to provide a standardized content framework for teaching resources.

[0077] Natural language generation models refer to algorithmic models that can transform structured data into natural language text. Specifically, they can be implemented using sequence generation models based on LSTM or GPT, and are used to transform teaching resource elements into highly readable learning materials.

[0078] Structured encapsulation refers to the process of organizing and storing text content in a standard format, specifically using XML or JSON formats to encapsulate data and ensure the availability of generated resources within the system.

[0079] Specifically, when the system detects that the existing teaching resource library lacks teaching content with corresponding ability difference tags, it first analyzes the learning objectives corresponding to the ability difference tags through the teaching resource generation model. For example, for the tag "insufficient ability to apply data analysis tools", it generates the task objective of "mastering Python data processing tools". Then, it retrieves the knowledge points associated with the task objective through the teaching knowledge graph, such as core skill requirements such as Pandas library operations and data visualization methods, forming a teaching framework that includes three parts: theoretical explanation, practical exercises, and outcome evaluation. Next, the natural language generation model automatically generates corresponding learning material texts based on this framework, such as operation guides with code examples and evaluation materials with test questions. Finally, the generated text content is standardized and packaged according to the chapter structure to form teaching resource units that can be directly pushed.

[0080] Through the above technical solution, this application achieves the dynamic generation of teaching resource units that are precisely matched to differences in abilities, solving the problem of the disconnect between teaching resources and job competency requirements in existing employment guidance. The systematic construction of teaching resources is ensured through knowledge graphs, avoiding the knowledge blind spots present in traditional manually compiled resources. Simultaneously, the automated generation process improves resource update efficiency, ensuring that students can access targeted learning content in a timely manner.

[0081] This application further proposes to determine the order of pushing teaching resource units, including: extracting the directed path from the current capability node to the target capability node according to the capability evolution path map; arranging the teaching resource units according to the numerical change of the node capability vector of each intermediate node in the directed path in the dimension corresponding to the capability difference label, so as to obtain the order of pushing teaching resource units.

[0082] in:

[0083] A directed path refers to the ability development route from the starting node to the ending node formed by the connection relationship between nodes in the ability evolution path graph. Specifically, it can be implemented by using graph traversal algorithm to extract the shortest or optimal path from the current ability node to the target ability node, and is used to describe the stage trajectory of students' ability improvement.

[0084] The numerical change order refers to the increasing or decreasing trend of the node capability vector in a specific dimension over time. Specifically, it can be achieved by using time series analysis to fit the trend of the node capability vector, which is used to reflect the dynamic change pattern in the dimension of capability difference.

[0085] Specifically, when determining the order of resource delivery, the system first searches for valid paths connecting a student's current skill level with the target skill level for their desired job within the skill evolution path graph. For example, if a student needs to improve their programming skills, the system will select path branches where the value of that skill level shows a step-like increase. Next, by analyzing the magnitude of numerical changes in the corresponding skill difference labels of adjacent nodes along the path, the system sorts the teaching resource units according to the gradient of skill improvement. For instance, if the data structure skill level of an intermediate node in the path increases by 30% compared to a preceding node, the corresponding data structure teaching resource unit will be prioritized for delivery.

[0086] Through the above technical solution, this application can generate a teaching resource push sequence that conforms to the law of ability development based on the dynamic difference between the student's current ability status and the requirements of the target position. This solution solves the problem of the mismatch between the resource push order and the actual ability improvement path in the traditional method, so that students can obtain teaching content that matches their current ability gap at each learning stage, thereby improving the pertinence of employment guidance and the scientific nature of path planning.

[0087] Exemplary Method

[0088] FIG. 3The diagram illustrates a flowchart of an AI-generated employment guidance teaching resource method according to an embodiment of this application, including: collecting a requirement description file for a target position, capability evolution data of multiple users who have successfully entered the target position, and current capability data of students to be guided; extracting a set of job capability tags based on the target position description file and mapping the set of job capability tags to standardized job capability vectors; constructing a capability evolution path graph based on the capability evolution data, the capability evolution path graph including multiple time-series nodes and corresponding node capability vectors; extracting student capability vectors corresponding to the standardized job capability vector structure based on the current capability data of students to be guided; and mapping the student capability vectors to the standardized job capability vector structure. Dimensions exceeding a preset threshold in the differences of standardized job competency vectors are mapped to a set of competency difference labels. Teaching resource units containing learning and assessment materials are matched from the teaching resource database based on the competency difference label set. If no match is found, a new teaching resource unit is generated based on the competency difference labels. The student competency vector and standardized job competency vector are matched with the node competency vectors in the competency evolution path graph to determine the current competency node and the target competency node. The order in which the teaching resource units are pushed is determined based on the node order between the current and target competency nodes. The teaching resource units are then pushed to the student's device according to this order.

[0089] In one example, extracting a set of job competency tags based on a target job description document includes: performing word segmentation and entity recognition on the target job description document to obtain competency text fragments related to job requirements; classifying and clustering the competency text fragments according to a pre-set competency classification lexicon and contextual semantic model to obtain a set of job competency tags.

[0090] In one example, mapping a set of job competency tags to a standardized job competency vector includes: encoding the set of job competency tags into vectors using a preset semantic embedding algorithm; and normalizing and aligning the vector encoding results with dimensions according to a preset job competency dimensional structure to obtain a standardized job competency vector.

[0091] In one example, constructing a capability evolution path graph based on capability evolution data includes: performing time-series labeling on the capability evolution data and extracting the node capability vectors corresponding to the time-series nodes; performing stage clustering on the node capability vectors according to a preset state transition modeling algorithm to obtain multiple capability evolution paths; and constructing a capability evolution path graph containing node capability vectors and their directed edge relationships based on the time sequence and capability transformation relationship between capability evolution paths.

[0092] In one example, extracting the student competency vector corresponding to the standardized job competency vector structure includes: uniformly formatting the student's current competency data and extracting the competency information fragment text of the student to be guided; constructing competency feature mapping rules based on the set of job competency tags, and extracting features from the competency information fragments according to the feature mapping rules to obtain an initial student competency vector matching the job competency tags; normalizing and reorganizing the dimensions of the initial student competency vector to obtain the student competency vector corresponding to the standardized job competency vector structure.

[0093] In one example, dimensional reorganization includes: rearranging the dimensions of the normalized student ability vector and padding missing values ​​with zeros according to the dimensional structure of the standardized job ability vector, to obtain a student ability vector that is consistent with the standardized job ability vector in terms of the number of dimensions and semantic structure.

[0094] In one example, mapping the dimension items in the difference between the student's ability vector and the standardized job ability vector that exceed a preset threshold to a set of ability difference labels includes: calculating the difference between the standardized job ability vector and the student's ability vector dimension by dimension to obtain an ability difference vector; filtering the dimension items in the ability difference vector that exceed the preset threshold as ability deficiency dimensions; and generating a set of ability difference labels based on the mapping relationship between the ability deficiency dimensions and the set of job ability labels.

[0095] In one example, generating a new teaching resource unit includes: generating task objectives that match ability difference labels using a pre-trained teaching resource generation model; retrieving knowledge points, skill requirements, and assessment requirements related to the task objectives using a pre-set teaching knowledge graph to obtain a draft teaching resource structure including the basic framework and elements of teaching resources; generating teaching resource text content containing learning materials and assessment materials based on the draft teaching resource structure using a pre-set natural language generation model; and structurally encapsulating the teaching resource text content to obtain the teaching resource unit.

[0096] In one example, determining the order of pushing teaching resource units includes: extracting the directed path from the current capability node to the target capability node based on the capability evolution path graph; arranging the teaching resource units according to the numerical change of the node capability vector of each intermediate node in the directed path in the dimension corresponding to the capability difference label, thus obtaining the order of pushing teaching resource units.

[0097] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0098] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. An AI-generated system for employment guidance teaching resources, characterized in that: include: The data acquisition module is used to collect the requirements description document of the target position, the ability evolution data of multiple users who have successfully joined the target position, and the current ability data of the students to be mentored; The job competency analysis module is used to extract a set of job competency tags based on the requirement description file and map the set of job competency tags into a standardized job competency vector. The successful path modeling module is used to construct a capability evolution path map based on the capability evolution data. The capability evolution path map includes multiple time-series nodes and corresponding node capability vectors. The student competency profile generation module is used to extract student competency vectors corresponding to the standardized job competency vector structure based on the current competency data of the students to be guided. The ability difference analysis module is used to map the dimension items in the difference between the student ability vector and the standardized job ability vector that exceed a preset threshold to a set of ability difference labels. The resource matching and generation module is used to match teaching resource units containing learning materials and assessment materials from the teaching resource database according to the set of ability difference tags. If no match is found, a new teaching resource unit is generated based on the set of ability difference tags. The path matching and push module is used to perform similarity matching between the student ability vector and the standardized job ability vector and the node ability vector in the ability evolution path graph, respectively, to determine the current ability node and the target ability node, and to determine the push order of the teaching resource unit according to the node order between the current ability node and the target ability node. The resource recommendation module is used to push the teaching resource units to the student's terminal device according to the push order.

2. The AI-generated employment guidance teaching resource system according to claim 1, characterized in that, The set of job competency tags extracted based on the requirements description document includes: The requirement description file is processed by word segmentation and entity recognition to obtain text fragments of capabilities related to job requirements; The ability text fragments are classified and clustered according to a preset ability classification lexicon and contextual semantic model to obtain the set of job ability tags.

3. The AI-generated employment guidance teaching resource system according to claim 2, characterized in that, The step of mapping the set of job competency tags into a standardized job competency vector includes: The set of job competency tags is vector-encoded using a preset semantic embedding algorithm; The vector encoding result is normalized and aligned with the dimensions according to the preset job competency dimension structure to obtain the standardized job competency vector.

4. The AI-generated employment guidance teaching resource system according to claim 1, characterized in that, The construction of the capability evolution path map based on the capability evolution data includes: The capability evolution data is time-series labeled, and the node capability vectors corresponding to the time-series nodes are extracted; The node capability vectors are clustered in stages according to a preset state transition modeling algorithm to obtain multiple capability evolution paths; Based on the temporal order and capability transformation relationship between the capability evolution paths, a capability evolution path graph containing node capability vectors and their directed edge relationships is constructed.

5. The AI-generated employment guidance teaching resource system according to claim 1, characterized in that, The extraction of student ability vectors corresponding to the standardized job ability vector structure includes: The current ability data of the students to be guided is uniformly formatted, and the text fragments of the ability information of the students to be guided are extracted. Ability feature mapping rules are constructed based on the set of job competency tags, and feature extraction is performed on the ability information fragments based on the feature mapping rules to obtain an initial student ability vector that matches the job competency tags. The initial student ability vector is normalized and its dimensions are reorganized to obtain a student ability vector corresponding to the standardized job ability vector structure.

6. The AI-generated employment guidance teaching resource system according to claim 5, characterized in that, The dimensional reorganization includes: rearranging the dimensions of the normalized student ability vector and padding missing values ​​with zeros according to the dimensional structure of the standardized job ability vector, so as to obtain a student ability vector with the same number of dimensions and semantic structure as the standardized job ability vector.

7. The AI-generated employment guidance teaching resource system according to claim 1, characterized in that, The step of mapping the dimension items in the difference between the student's ability vector and the standardized job ability vector that exceed a preset threshold to a set of ability difference labels includes: The standardized job competency vector and the student competency vector are calculated dimension by dimension to obtain the competency difference vector. Dimensions in the capability difference vector that are higher than a preset threshold are selected as dimensions of capability deficiency. Based on the mapping relationship between the capability deficiency dimension and the job capability tag set, the capability difference tag set is generated.

8. The AI-generated employment guidance teaching resource system according to claim 1, characterized in that, The generation of new teaching resource units includes: A pre-trained teaching resource generation model is used to generate task objectives that match the set of ability difference labels. By retrieving knowledge points, skill requirements, and assessment requirements related to the task objectives from a pre-set teaching knowledge graph, a draft teaching resource structure including the basic framework and elements of teaching resources is obtained. Based on the aforementioned teaching resource structure draft, a pre-defined natural language generation model is used to generate teaching resource text content containing learning materials and assessment materials. The text content of the teaching resources is structured and encapsulated to obtain the teaching resource unit.

9. The AI-generated employment guidance teaching resource system according to claim 1, characterized in that, The process of determining the order in which the teaching resource units are pushed includes: Based on the capability evolution path graph, a directed path from the current capability node to the target capability node is extracted; The teaching resource units are arranged according to the numerical change order of the node capability vectors of each intermediate node in the directed path in the dimension corresponding to the capability difference label, so as to obtain the push order of the teaching resource units.

10. An AI-generated method for employment guidance teaching resources, employing the system described in any one of claims 1 to 9, characterized in that, include: Collect the requirements description document for the target position, the capability evolution data of multiple users who have successfully joined the target position, and the current capability data of the students to be mentored; Based on the requirements description document, a set of job competency tags is extracted, and the set of job competency tags is mapped into a standardized job competency vector. A capability evolution path map is constructed based on the capability evolution data. The capability evolution path map includes multiple time-series nodes and corresponding node capability vectors. Based on the current ability data of the students to be guided, extract the student ability vector corresponding to the standardized job ability vector structure; The dimension items in the difference between the student's ability vector and the standardized job ability vector that exceed a preset threshold are mapped to a set of ability difference labels; Based on the set of ability difference tags, teaching resource units containing learning materials and assessment materials are matched from the teaching resource database. If no match is found, a new teaching resource unit is generated based on the set of ability difference tags. The student ability vector and the standardized job ability vector are matched with the node ability vectors in the ability evolution path graph to determine the current ability node and the target ability node. The order of pushing the teaching resource units is determined according to the node order between the current ability node and the target ability node. The teaching resource units are pushed to the student's device in the order specified.

Images