Ideological and political attainment intelligent evaluation and hierarchical guidance method and system for young groups

Abstract

The invention provides an ideological and political attainment intelligent evaluation and hierarchical guidance method and system for young groups, and relates to the technical field of intelligent education, and the method comprises the four steps: construction of a preset database, data collection, attainment quantification and division, and hierarchical guidance. Multi-source heterogeneous data such as dominant cognition, recessive behaviors and subjective texts are automatically collected through technical means, the evaluation basis is more comprehensive and objective, then an algorithm model is introduced, deep quantitative analysis is conducted on the data, a comprehensive index and a layered profile are generated, dynamic and accurate evaluation of user attainment is achieved, and finally, based on a rule library and a label library, the user experience is improved. According to the invention, the conversion from finding resources by people to finding people by resources is realized, an accurate personalized guidance scheme is provided for users of different levels and different short boards, and the ideological and political education efficiency is greatly improved. According to the method, the modern information technology means can be comprehensively utilized, automatic and intelligent evaluation is achieved, and a brand-new technical scheme of dynamic and personalized layered guidance can be achieved.

Description

A Method and System for Assessing and Differentiating the Ideological and Political Literacy of Young People Technical Field

[0001] This invention relates to the field of smart education technology, and in particular to a method and system for assessing and providing tiered guidance on ideological and political literacy among young people. Background Technology

[0002] Conducting scientific and effective assessments and guidance of the ideological and political literacy of young people is a core aspect of ideological and political education in the new era. However, currently prevalent traditional methods, such as written or online questionnaires based on fixed question sets, standardized examinations, and subjective evaluations, have significant limitations at the technical level and are no longer suitable for the practical needs of precise and personalized education. These methods essentially rely on the instantaneous, subjective responses of the test-takers to pre-set questions at a specific moment, resulting in extremely limited data dimensions, almost entirely confined to the explicit cognitive level. They fail to effectively capture the real and stable behavioral patterns and inner emotional tendencies of young people in their daily learning and online spaces, causing the objectivity of the assessment results to be significantly compromised by factors such as the social expectation effect. More importantly, this "one-off snapshot" assessment is static and isolated, unable to depict the continuous evolution of individual ideological dynamics, nor capable of providing early warnings and interventions for potential development trends, leading to a lack of foresight in educational guidance.

[0003] In the most crucial application stage, due to the lack of detailed characterization of individual multidimensional ability shortcomings, subsequent guidance measures often have to adopt a "one-size-fits-all" extensive model, failing to achieve the transformation from "people looking for resources" to "resources looking for people," which greatly restricts the allocation efficiency of ideological and political education resources and the final guidance effectiveness. Therefore, this invention proposes a method and system for assessing and guiding the ideological and political literacy of young people in a tiered manner to solve the problems existing in the prior art. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to propose a method and system for intelligent assessment and tiered guidance of ideological and political literacy among young people. This system can comprehensively utilize modern information technology to achieve automated and intelligent assessment, and provide a novel technical solution for dynamic and personalized tiered guidance, thereby solving the problems existing in the prior art.

[0005] To achieve the objectives of this invention, the invention is implemented through the following technical solution: A method for intelligent assessment and tiered guidance of ideological and political literacy for young people, characterized by the following steps: Step 1: Construction of a preset database. A guidance strategy rule base and a structured content resource base are pre-constructed; Step 2: Data collection. Multi-source heterogeneous data of users are collected, including explicit cognitive data, implicit behavioral data, and subjective text data; Step 3: Literacy quantification and classification. Based on the acquired multi-source heterogeneous data, the user's dimensional scores in multiple preset dimensions are calculated, and a comprehensive index of ideological and political literacy is generated by fusing the scores of each dimension. Then, the user is classified into a predefined literacy level according to the comprehensive index, thereby generating a tiered guidance profile containing the literacy level and the scores of each dimension; Step 4: Tiered guidance. The tiered guidance profile is matched with the guidance strategy rule base to obtain guidance strategies. Then, matching learning resources are retrieved from the structured content resource base according to the guidance strategies and organized into personalized learning resource paths and pushed to the user to complete the tiered guidance of ideological and political literacy.

[0006] A further improvement is that, in step one, the guidance strategy rules of the guidance strategy rule base are: conditional logical expressions containing literacy levels and scores of each dimension as variables, and the rules are structured and encoded before being stored in the database.

[0007] A further improvement is made in the following step: In step one, the structured content resource library stores ideological and political learning resources, and each resource is labeled with a structured tag that includes the content theme, difficulty level, and target dimension.

[0008] Further improvements are made in the following aspects: In step two, explicit cognitive data includes users' answers to objective questions and the time taken to answer them; implicit behavioral data includes users' behavioral sequence data within the designated learning platform and interactive behavioral data generated in the interactive module; and subjective text data includes text content data input by users in response to open-ended questions.

[0009] A further improvement is made in step three, where the scores for multiple preset dimensions include theoretical cognition score, behavioral tendency score, and emotional attitude score. The theoretical cognition score is calculated by comparing the user's answer with the standard answer and combining the answering time. The behavioral tendency score is calculated by analyzing behavioral sequence data and combining interactive behavior data. The emotional attitude score is obtained by analyzing text content data using natural language processing technology.

[0010] A further improvement is that, in step three, the integrated index of ideological and political literacy is derived by combining the scores of theoretical cognition dimension, behavioral tendency dimension, and emotional attitude dimension through a pre-trained weighted fusion model.

[0011] A further improvement is made in the following way: In step four, the specific method for pushing personalized learning resource paths is as follows: S1, match the literacy levels and scores of each dimension in the hierarchical guidance profile with the predefined rules in the guidance strategy rule base to obtain the guidance strategy identifier for the user; S2, then, based on the guidance strategy identifier, retrieve a list of learning resource identifiers with corresponding tags from the structured content resource base using a tag matching algorithm; S3, then organize the retrieved learning resources into a personalized learning path according to a preset logic and push it.

[0012] A system for assessing and providing tiered guidance on ideological and political literacy among young people includes a database construction module for building and storing a guidance strategy rule base and a structured content resource base; a data acquisition module for collecting multi-source heterogeneous data from users; a literacy analysis module for analyzing the collected multi-source heterogeneous data to generate tiered guidance profiles; and a tiered guidance module for matching the tiered guidance profiles with the data in the database construction module to generate personalized learning paths.

[0013] The beneficial effects of this invention are as follows: This invention automatically collects multi-source heterogeneous data such as explicit cognition, implicit behavior, and subjective text through technical means, making the assessment basis more comprehensive and objective. Then, an algorithm model is introduced to conduct in-depth quantitative analysis of the data, generating a comprehensive index and hierarchical profile, realizing a dynamic and accurate assessment of user literacy. Finally, based on the rule base and tag base, it realizes the transformation from people finding resources to resources finding people, providing accurate and personalized guidance solutions for users at different levels and with different shortcomings, greatly improving the effectiveness of ideological and political education. Detailed Implementation

[0014] To enhance understanding of the present invention, the present invention will be further described in detail below with reference to embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation on the scope of protection of the present invention.

[0015] This embodiment proposes a method for assessing and guiding the ideological and political literacy of young people, including the following steps: Step 1: Construction of a Pre-built Database. A guidance strategy rule base and a structured content resource base are pre-built. The purpose of the guidance strategy rule base is to define a series of "condition-action" rules. For example, if a user belongs to the cultivation level and their theoretical cognition score is below 60, a basic theory reinforcement strategy is triggered. These natural language rules are then converted into a computer-processable structured form. Each rule contains three fields: rule ID (unique identifier), trigger condition (a logical expression composed of literacy level and scores of each dimension, e.g., level == "cultivation level" && theoretical cognition score < 60), and guidance strategy identifier (e.g., STRATEGY_THEORY_BASIC). These rules are stored in the database to form the guidance strategy rule base.

[0016] The structured content resource library collects learning resources related to ideology and politics, such as theoretical articles, teaching videos, case studies, and interactive Q&A. Each resource is labeled with structured tags, including: content theme tags (e.g., "basic principles"); difficulty level tags (e.g., "beginner," "intermediate," and "advanced"); and target dimension tags (e.g., "strengthening theoretical understanding," "guiding value choices," and "cultivating patriotic feelings").

[0017] These tags can be created manually or automatically generated by analyzing the resource content using natural language processing technology. Ultimately, all tagged resources are stored in a database, forming a structured content resource library.

[0018] Step Two: Data Collection. Through client-side interaction with users, multi-source heterogeneous data is automatically collected. This multi-source heterogeneous data includes explicit cognitive data, implicit behavioral data, and subjective text data. Specifically: Explicit cognitive data includes user answers to objective questions and the time taken to answer them. The system pushes standardized, quantifiable objective questions (such as multiple-choice and true / false questions) to the user's client (e.g., an app or webpage). The system accurately records user answers and answer times (accurate to milliseconds). Implicit behavioral data includes user behavior sequence data within the designated learning platform and interactive behavior data generated in interactive modules. Through a behavior monitoring SDK integrated into the client, user behavior logs within the platform are collected seamlessly, including: page dwell time, content clickstream sequence, video viewing completion rate, and interactive behavior data such as supporting / opposing stances generated during the interaction process. Subjective text data includes text content data input by users in response to open-ended questions. That is, open-ended questions (e.g., "Please talk about your views on a certain social hot topic") are presented to users through the client, and the freely input text content data of users is collected.

[0019] Correspondingly, all collected data is associated with user IDs, timestamped, and transmitted to the server via the network.

[0020] Step 3: Literacy Quantification and Classification. Based on the acquired multi-source heterogeneous data, user scores are calculated across multiple preset dimensions. These dimensions include theoretical cognition, behavioral tendency, and emotional attitude scores. Specifically: The theoretical cognition score is calculated by comparing user answers with standard answers and considering answering time. A base score is obtained by comparing user answers with standard answers and calculating the accuracy rate. Efficiency points are awarded to users who answer quickly and correctly, resulting in a final theoretical cognition score. The behavioral tendency score is calculated by analyzing behavioral sequence data and combining it with interactive behavior data. A collaborative filtering algorithm is used to calculate the similarity between user behavior sequences and preset high-quality benchmark user behavior patterns, resulting in a behavioral consistency score. Simultaneously, interactive behavior data (such as support for positive viewpoints) is quantified and assigned a value selection score, resulting in a final behavioral tendency score. The emotional attitude score is obtained by analyzing text content data using natural language processing (NLP) technology. First, preprocessing such as word segmentation and noise reduction is performed. Then, a sentiment analysis model (LSTM) is used to analyze the sentiment polarity (positive / negative) and intensity of the text to generate a sentiment tendency score. Next, a topic model (LDA) is used to analyze whether the text topic is healthy and conforms to mainstream values ​​to generate a topic health score. Finally, a sentiment attitude dimension score is synthesized.

[0021] Then, a comprehensive index of ideological and political literacy is generated based on the fusion of scores from each dimension. Specifically, the scores from the three dimensions are input into a pre-trained weighted fusion model (Gradient Boosting Decision Tree (GBDT) model). This model is trained using machine learning on a large amount of historical data and can automatically learn the weights of each dimension. The model outputs a comprehensive index of ideological and political literacy. Based on the preset range of this comprehensive index, users are divided into corresponding literacy levels. Correspondingly, the comprehensive index of ideological and political literacy is represented by a constant, so the literacy levels are divided as follows: (0, 60) is the nurturing level, (60, 85) is the follow-up level, and (85, 100) is the advanced level.

[0022] Finally, a structured data object called a hierarchical guided profile is generated, which contains the user's literacy level and specific scores for each dimension, comprehensively depicting the user's literacy status.

[0023] Step 4: Layered guidance. Based on the layered guidance profile, the guidance strategy rule base is matched to obtain the guidance strategy. Then, according to the guidance strategy, matching learning resources are retrieved from the structured content resource base and organized into a personalized learning resource path and pushed to the user to complete the layered guidance of ideological and political literacy.

[0024] The specific steps are as follows: S1. Match the competency level and scores of each dimension in the hierarchical guidance profile with predefined rules in the guidance strategy rule base to obtain a guidance strategy identifier for the user. For example, if the profile information matches the rule "Cultivation Level && Low Theoretical Cognition Score", the corresponding "Basic Theory Reinforcement" strategy identifier will be automatically triggered. S2. Then, based on the obtained guidance strategy identifier, quickly retrieve matching learning resources from the structured content resource library using a tag matching algorithm. For example, the "Basic Theory Reinforcement" strategy may correspond to resources with "Content Topic = Basic Principles" and "Difficulty Level = Beginner". S3. Then, organize the retrieved learning resources into a personalized learning path according to a preset logic (from easy to difficult) and push it to the user's client. The first learning task in the path is actively pushed to the user's client to guide them to start learning, thus completing a complete "assessment-guidance" closed loop.

[0025] A system for assessing and providing tiered guidance on ideological and political literacy among young people includes a database construction module for building and storing a guidance strategy rule base and a structured content resource base; a data acquisition module for collecting multi-source heterogeneous data from users; a literacy analysis module for analyzing the collected multi-source heterogeneous data to generate tiered guidance profiles; and a tiered guidance module for matching the tiered guidance profiles with the data in the database construction module to generate personalized learning paths.

[0026] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the present invention without departing from its framework and scope of application, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for assessing and providing tiered guidance on ideological and political literacy among young people, characterized by: The process includes the following steps: Step 1: Construction of the Pre-set Database. A pre-built guidance strategy rule base and a structured content resource base are constructed. Step 2: Data Collection. This involves collecting multi-source heterogeneous data from users, including explicit cognitive data, implicit behavioral data, and subjective textual data. Step 3: Literacy Quantification and Classification. Based on the acquired multi-source heterogeneous data, user scores are calculated across multiple pre-set dimensions. These scores are then integrated to generate a comprehensive index of ideological and political literacy. Users are then classified into predefined literacy levels based on this comprehensive index, resulting in a tiered guidance profile containing the literacy levels and scores across each dimension. Step 4: Tiered Guidance. The tiered guidance profile is matched against the guidance strategy rule base to obtain guidance strategies. Matching learning resources are then retrieved from the structured content resource base according to these strategies and organized into personalized learning resource paths, which are then pushed to users to complete the tiered guidance of ideological and political literacy.

2. The method for assessing and providing tiered guidance on ideological and political literacy among young people according to claim 1, characterized in that: In step one, the guidance strategy rules of the guidance strategy rule base are: conditional logical expressions containing literacy levels and scores of each dimension as variables, and the rules are structured and encoded before being stored in the database.

3. The method for assessing and providing tiered guidance on ideological and political literacy among young people according to claim 1, characterized in that: In step one, the structured content resource library stores ideological and political learning resources, and each resource is labeled with a structured tag that includes the content theme, difficulty level, and target dimension.

4. The method for assessing and providing tiered guidance on ideological and political literacy among young people according to claim 1, characterized in that: In step two, explicit cognitive data includes users' answers to objective questions and the time taken to answer them; implicit behavioral data includes users' behavioral sequence data within the designated learning platform and interactive behavioral data generated in the interactive module; and subjective text data includes text content data input by users in response to open-ended questions.

5. The method for assessing and providing tiered guidance on ideological and political literacy among young people according to claim 1, characterized in that: In step three, the scores of multiple preset dimensions include theoretical cognition score, behavioral tendency score, and emotional attitude score. The theoretical cognition score is calculated by comparing the user's answer with the standard answer and combining the answering time. The behavioral tendency score is calculated by analyzing behavioral sequence data and combining interactive behavior data. The emotional attitude score is obtained by analyzing text content data using natural language processing technology.

6. The method for assessing and providing tiered guidance on ideological and political literacy among young people according to claim 1, characterized in that: In step three, the integrated index of ideological and political literacy is generated by combining the scores of theoretical cognition dimension, behavioral tendency dimension, and emotional attitude dimension through a pre-trained weighted fusion model.

7. The method for assessing and providing tiered guidance on ideological and political literacy among young people according to claim 1, characterized in that: In step four, the specific method for pushing personalized learning resource paths is as follows: S1, match the literacy levels and scores of each dimension in the hierarchical guidance profile with the predefined rules in the guidance strategy rule base to obtain the guidance strategy identifier for the user; S2, then, based on the guidance strategy identifier, retrieve a list of learning resource identifiers with corresponding tags from the structured content resource base using a tag matching algorithm; S3, then organize the retrieved learning resources into a personalized learning path according to a preset logic and push it.

8. A system applied to the method for assessing and providing tiered guidance on ideological and political literacy among young people as described in claim 1, characterized in that: Includes a database building module for building and storing the bootstrapping policy rule base and structured content resource base; The data acquisition module is used to collect multi-source heterogeneous data from users; the literacy analysis module is used to analyze the collected multi-source heterogeneous data and generate hierarchical guidance profiles. The hierarchical guidance module is used to match the hierarchical guidance profile with the data in the database construction module to generate personalized learning paths.