Block chain-based mutual-aid co-learning education system and method

Abstract

The invention belongs to the technical field of block chain education, and particularly relates to a mutual-aid co-learning education system and method based on a block chain. According to the invention, the intelligent contract automatically generates and executes the learning plan, the evaluation standard and the incentive strategy, reduces the manual intervention and management cost, improves the system operation efficiency, enables multiple verification nodes to participate in the consensus together, ensures that the evaluation process is open and transparent, enables learners to have a sense of trust on the result, and enables a tutor to obtain fair teaching feedback. Based on multi-dimensional data such as learning progress, result quality and interaction contribution, a differential excitation strategy is designed, so that the learner is encouraged to learn actively, and the tutor and the peer are encouraged to provide high-quality teaching and review.

Description

Technical Field

[0001] The present invention belongs to the technical field of blockchain education, and particularly relates to a mutual assistance and co - learning education system and method based on blockchain. Background Art

[0002] With the rapid development of information technology, the Internet has become an important carrier of modern education, and the traditional education model is facing challenges in aspects such as personalization, decentralization, and resource sharing. The traditional education model has the following deficiencies: First, the distribution of educational resources is uneven and it is difficult to share them, resulting in high - quality educational resources being concentrated in a few institutions or regions; second, the existing education evaluation and certification system is easily interfered by human factors and lacks transparency and credibility; third, the interaction and cooperation mechanism in the learning process is relatively single, and it is unable to fully stimulate the enthusiasm of students for autonomous learning and mutual assistance and co - learning.

[0003] As a distributed ledger and information security technology, blockchain technology has characteristics such as decentralization, immutability, data traceability, and smart contracts. These characteristics provide a technical foundation and guarantee for building a new education ecosystem. In recent years, blockchain technology has made breakthrough progress in many fields such as finance, logistics, and healthcare. Its advantages in data credibility, transparency, and security have attracted wide attention and exploration in the education field.

[0004] The mutual assistance and co - learning education method based on blockchain emerged under this background. This method uses blockchain technology to build an open and transparent educational resource sharing platform, and through smart contracts, it automatically executes functions such as teaching evaluation, learning incentives, and knowledge sharing, effectively solving problems such as uneven resource allocation, information opacity, and insufficient incentives in traditional education. At the same time, through a multi - party cooperation mechanism, this method encourages mutual assistance and communication among learners to promote common progress, and uses decentralized technical means to ensure the authenticity and immutability of data, providing a fair and credible learning environment for each participating subject.

[0005] Traditional teaching models mainly rely on fixed courses and unified evaluation criteria, and it is difficult to provide a dynamically matched learning plan and assessment scheme according to the individual needs and ability differences of learners; at the same time, the teaching quality and styles of tutors vary greatly, and there is no effective mechanism to finely connect teaching content and evaluation criteria with learners' needs. Most platforms lack a transparent and multi - dimensional incentive system, and it is often difficult to form a closed - loop feedback and dynamic reward for learners' completion, tutors' teaching quality, and reviewers' fairness. As a result, learners lack motivation, tutors have low enthusiasm, and reviewers have limited participation. Summary of the Invention

[0006] The objective of the present invention is to provide a mutual-aid and co-learning education system and method based on blockchain, which can enhance the credibility, personalization level, and operation efficiency of online education, taking into account data security and privacy protection, and having significant practical value and promotion prospects.

[0007] The technical solutions adopted by the present invention are specifically as follows:

[0008] A mutual-aid and co-learning education method based on blockchain, comprising:

[0009] Obtaining a decentralized education mutual-aid blockchain network, which includes learner nodes, tutor nodes, and verification nodes;

[0010] Obtaining the learning demand data and learning ability proof data of learner nodes, and obtaining learning contract information based on the learning demand data and learning ability proof data;

[0011] Obtaining the teaching content data and evaluation standard data of tutor nodes, and obtaining co-learning protocol information based on the teaching content data and evaluation standard data;

[0012] Obtaining the interaction data, learning achievement data, and evaluation record data of verification nodes, and obtaining consensus information based on the interaction data, learning achievement data, and evaluation record data;

[0013] Obtaining an incentive strategy based on the learning contract information, co-learning protocol information, and consensus information, and obtaining co-learning behavior rewards based on the incentive strategy.

[0014] In a preferred solution, the step of obtaining the learning demand data and learning ability proof data of learner nodes, and obtaining learning contract information based on the learning demand data and learning ability proof data includes:

[0015] Obtaining the learning demand data and learning ability proof data of learner nodes;

[0016] Obtaining a corresponding learning demand matrix according to the learning demand data, and obtaining a corresponding plurality of learning demand vectors according to the learning demand matrix;

[0017] Obtaining a corresponding learning ability proof matrix according to the learning ability proof data, and obtaining a learning ability proof vector corresponding to each learning demand vector according to the learning ability proof matrix;

[0018] Obtaining learning behavior values according to the plurality of learning demand vectors and the plurality of learning ability proof vectors;

[0019] Obtaining a learning contract table, where the learning contract table includes a plurality of learning behavior intervals and the learning contract information corresponding to each learning behavior interval;

[0020] Obtain the corresponding learning contract information from the learning contract table according to the learning behavior interval corresponding to the learning behavior value.

[0021] In a preferred solution, the steps of obtaining the teaching content data and evaluation criterion data of the tutor node and obtaining the co-learning protocol information according to the teaching content data and evaluation criterion data include:

[0022] Obtain the teaching content data and evaluation criterion data of the tutor node;

[0023] Obtain the corresponding teaching content matrix according to the teaching content data, and obtain the corresponding multiple teaching content vectors according to the teaching content matrix;

[0024] Obtain the corresponding evaluation criterion matrix according to the evaluation criterion data, and obtain the corresponding multiple evaluation criterion vectors according to the evaluation criterion matrix;

[0025] Obtain the historical teaching behavior data of the tutor node, and obtain the corresponding historical teaching feedback according to the historical teaching behavior data;

[0026] Obtain the teaching quality value according to the multiple teaching content vectors, multiple evaluation criterion vectors and historical teaching feedback;

[0027] Obtain the co-learning protocol table, where the co-learning protocol table includes multiple teaching quality intervals and the co-learning protocol information corresponding to each teaching quality interval;

[0028] Obtain the corresponding co-learning protocol information from the co-learning protocol table according to the teaching quality interval corresponding to the teaching quality value.

[0029] In a preferred solution, the steps of obtaining the historical teaching behavior data of the tutor node and obtaining the corresponding historical teaching feedback according to the historical teaching behavior data include:

[0030] Obtain the historical teaching behavior data of the tutor node;

[0031] Obtain the corresponding historical teaching behavior matrix according to the historical teaching behavior data, and obtain the corresponding multiple historical teaching behavior vectors according to the historical teaching behavior matrix;

[0032] Obtain the corresponding historical teaching value according to the multiple historical teaching behavior vectors;

[0033] Obtain the historical teaching table, where the historical teaching table includes multiple historical teaching intervals and the historical teaching feedback corresponding to each historical teaching interval;

[0034] Obtain the corresponding historical teaching feedback from the historical teaching table according to the historical teaching interval corresponding to the historical teaching value.

[0035] In a preferred embodiment, the steps of obtaining the historical teaching behavior data of the tutor node include:

[0036] Obtaining teaching behavior values based on multiple teaching content vectors and multiple evaluation criterion vectors;

[0037] Obtaining a teaching behavior table, where the teaching behavior table includes multiple teaching behavior intervals and the corresponding historical teaching durations for each teaching behavior interval;

[0038] Obtaining the corresponding historical teaching duration from the teaching behavior table according to the teaching behavior interval corresponding to the teaching behavior value;

[0039] Collecting the acquisition time node of the learning contract information and marking it as the end time of the historical teaching period;

[0040] Obtaining the start time of the historical teaching period according to the historical teaching duration and the end time of the historical teaching period, and constructing the historical teaching period;

[0041] Obtaining the historical teaching behavior data within the historical teaching period.

[0042] In a preferred embodiment, the steps of obtaining the interaction data, learning outcome data, and evaluation record data of the verification node and obtaining the consensus information based on the interaction data, learning outcome data, and evaluation record data include:

[0043] Obtaining the interaction data, learning outcome data, and evaluation record data of the verification node;

[0044] Obtaining the corresponding interaction matrix according to the interaction data, and obtaining the corresponding multiple interaction vectors according to the interaction matrix;

[0045] Obtaining the corresponding learning outcome matrix according to the learning outcome data of this node, and obtaining the corresponding multiple learning outcome vectors according to the learning outcome matrix;

[0046] Obtaining the corresponding evaluation record matrix according to the evaluation record data, and obtaining the corresponding multiple evaluation record vectors according to the evaluation record matrix;

[0047] Obtaining a consensus value based on the multiple interaction vectors, multiple learning outcome vectors, and multiple evaluation record vectors;

[0048] Obtaining a consensus standard value, and obtaining consensus information according to the consensus value.

[0049] In a preferred embodiment, the steps of obtaining a consensus standard value and obtaining consensus information according to the consensus value include:

[0050] Obtaining a consensus standard value;

[0051] Obtaining a consensus coefficient according to the consensus standard value and the consensus value;

[0052] Obtain a consensus table, where the consensus table includes multiple consensus coefficient intervals and the consensus information corresponding to each consensus coefficient interval;

[0053] Obtain the corresponding consensus coefficient from the consensus table according to the consensus coefficient interval corresponding to the consensus coefficient.

[0054] In a preferred solution, the steps of obtaining an incentive strategy according to the learning contract information, the co - learning protocol information, and the consensus information, and obtaining the co - learning behavior reward according to the incentive strategy include:

[0055] Obtain the corresponding learning behavior value, teaching quality value, and consensus value according to the learning contract information, the co - learning protocol information, and the consensus information respectively;

[0056] Obtain an incentive value according to the learning behavior value, the teaching quality value, and the consensus value;

[0057] Obtain an incentive table, where the incentive table includes multiple incentive value intervals and the incentive rewards corresponding to each incentive value interval;

[0058] Obtain the corresponding incentive reward from the incentive table according to the incentive value interval corresponding to the incentive value;

[0059] Obtain the co - learning behavior reward according to the incentive reward.

[0060] The present invention also provides a mutual - aid co - learning education system based on a blockchain for the above - mentioned mutual - aid co - learning education method based on a blockchain, including:

[0061] A blockchain module for obtaining a decentralized education mutual - aid blockchain network, where the education mutual - aid blockchain network includes learner nodes, tutor nodes, and verification nodes;

[0062] A learning contract module for obtaining the learning requirement data and learning ability proof data of the learner nodes, and obtaining learning contract information according to the learning requirement data and learning ability proof data;

[0063] A co - learning protocol module for obtaining the teaching content data and evaluation criterion data of the tutor nodes, and obtaining co - learning protocol information according to the teaching content data and evaluation criterion data;

[0064] A consensus module for obtaining the interaction data, learning achievement data, and evaluation record data of the verification nodes, and obtaining consensus information according to the interaction data, learning achievement data, and evaluation record data;

[0065] A co - learning reward module for obtaining an incentive strategy according to the learning contract information, the co - learning protocol information, and the consensus information, and obtaining the co - learning behavior reward according to the incentive strategy.

[0066] And, a blockchain-based mutual assistance and co-learning education terminal, comprising:

[0067] One or more processors;

[0068] A storage device on which one or more programs are stored;

[0069] When the one or more programs are executed by the one or more processors, the one or more processors implement a blockchain-based mutual assistance and co-learning education method.

[0070] The technical effects achieved by the present invention are as follows:

[0071] In the present invention, a learning plan, evaluation criteria, and incentive strategy are automatically generated and executed by a smart contract, reducing manual intervention and management costs, improving the operating efficiency of the system. Multiple verification nodes jointly participate in the consensus to ensure that the evaluation process is open and transparent, learners have more trust in the results, and tutors can also obtain fair teaching feedback. Based on multi-dimensional data such as learning progress, achievement quality, and interaction contributions, a differentiated incentive strategy is designed to encourage learners to actively learn and also motivate tutors and peers to provide high-quality teaching and review. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 is a flowchart of the method provided by the present invention;

[0073] Figure 2 is a system module diagram provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0074] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention is provided in conjunction with the accompanying drawings of the specification.

[0075] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar promotions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0076] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in a preferred embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0077] Thirdly, the present invention is described in detail in conjunction with the schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of explanation, the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein.

[0078] Please refer to the attached Figure 1 As shown, a mutual-aid and co-learning education method based on blockchain is provided, including:

[0079] S1. Obtain a decentralized education mutual-aid blockchain network, where the education mutual-aid blockchain network includes learner nodes, tutor nodes, and verification nodes;

[0080] S2. Obtain the learning requirement data and learning ability proof data of the learner nodes, and obtain learning contract information according to the learning requirement data and learning ability proof data;

[0081] S3. Obtain the teaching content data and evaluation criterion data of the tutor nodes, and obtain co-learning protocol information according to the teaching content data and evaluation criterion data;

[0082] S4. Obtain the interaction data, learning achievement data, and evaluation record data of the verification nodes, and obtain consensus information according to the interaction data, learning achievement data, and evaluation record data;

[0083] S5. Obtain an incentive strategy according to the learning contract information, co-learning protocol information, and consensus information, and obtain co-learning behavior rewards according to the incentive strategy.

[0084] In the above steps S1 to S5, a decentralized educational mutual assistance blockchain network is deployed. This network consists of three types of nodes: learner nodes, which are responsible for submitting learning requirements and proof of capabilities; tutor nodes, which are responsible for publishing teaching content and evaluation criteria; and verification nodes, which are responsible for recording and verifying learning interactions, results, and evaluations. Learner nodes submit their "learning requirement data" (such as expected learning topics, schedule, etc.) and "proof of learning ability data" (such as previous grades, skill certificates, etc.). Based on this data, "learning contract information" is generated, clarifying learning objectives, progress arrangements, and assessment indicators. Tutor nodes upload "teaching content data" (such as courseware, videos, exercises) and "evaluation criterion data" (such as grading rules, passing marks). Based on the teaching content and evaluation criteria, "co-learning protocol information" is generated, defining the rights and responsibilities, evaluation processes, and interaction methods of both parties during the teaching process. Verification nodes collect and record on the blockchain: interaction data, including question-and-answer, discussion, and assignment submission records between learners and tutors; learning result data, including test scores, project reports, and assignment grades; evaluation record data, including tutors' evaluations of learners, peer evaluations, or third-party assessment results. Based on the above data, the blockchain network forms "consensus information" through a consensus mechanism to ensure the fairness and transparency of the learning process and results. Combining the "learning contract information", "co-learning protocol information", and "consensus information", an "incentive strategy" is automatically calculated and generated, such as rewards for achieving learning progress, rewards for high-quality Q&A, rewards for peer evaluation contributions, etc. According to the incentive strategy, "co-learning behavior rewards" are distributed to the corresponding node wallets in the form of tokens or points to encourage all parties to actively participate in high-quality interactions. Smart contracts automatically generate and execute learning plans, evaluation criteria, and incentive strategies, reducing manual intervention and management costs and improving operational efficiency. Multiple verification nodes jointly participate in the consensus to ensure the openness and transparency of the evaluation process, making learners more trusting of the results, and tutors can also obtain fair teaching feedback. Based on multi-dimensional data such as learning progress, result quality, and interaction contributions, differentiated incentive strategies are designed to encourage learners to take the initiative to learn and also motivate tutors and peers to provide high-quality teaching and reviews.

[0085] In a preferred implementation manner, the steps of obtaining the learning requirement data and proof of learning ability data of the learner node and obtaining the learning contract information according to the learning requirement data and proof of learning ability data include:

[0086] S201. Obtain the learning requirement data and proof of learning ability data of the learner node;

[0087] S202. Obtain the corresponding learning requirement matrix according to the learning requirement data, and obtain a plurality of corresponding learning requirement vectors according to the learning requirement matrix;

[0088] S203. Obtain the corresponding learning ability proof matrix according to the learning ability proof data, and obtain the learning ability proof vector corresponding to each learning requirement vector according to the learning ability proof matrix;

[0089] S204. Obtain the learning behavior value according to multiple learning requirement vectors and multiple learning ability proof vectors;

[0090] S205. Obtain the learning contract table, where the learning contract table includes multiple learning behavior intervals and the learning contract information corresponding to each learning behavior interval;

[0091] S206. Obtain the corresponding learning contract information from the learning contract table according to the learning behavior interval corresponding to the learning behavior value.

[0092] In the above steps S201 to S206, two types of data are collected from the learner node: The learning requirement data includes learning objectives (such as skill categories), preferences (such as learning methods, rhythms), etc.; The learning ability proof data includes previous grades, certification certificates, evaluation reports, etc. These data are stored in a decentralized manner or directly uploaded to the chain to ensure integrity and security. Map the collected learning requirement data to a high-dimensional feature space to form a matrix form. The rows of the matrix represent different requirement dimensions (such as knowledge point categories, difficulty levels, duration preferences, etc.), and the columns represent specific numerical values or category codes. Through matrix decomposition or embedding techniques (such as principal component analysis, deep autoencoders, etc.), transform the learning requirement matrix into multiple low-dimensional vectors, and each vector corresponds to a subset of learning requirements. Map the learner's ability proof data to another high-dimensional feature space. The rows of the matrix can include indicators such as knowledge mastery, practical experience, evaluation scores, etc., and the columns are the corresponding numerical values or codes. Use a dimensionality reduction or embedding method similar to the requirement vectorization to obtain the ability proof vector corresponding to each learning requirement vector one by one. Perform a matching calculation on each pair of "learning requirement vector" and "ability proof vector" to obtain the corresponding learning behavior value. The calculation formula for the learning behavior value is In the formula, L represents the learning behavior value, t represents the numbers of multiple learning requirement vectors and the corresponding multiple learning ability proof vectors, t = 1, 2, 3... u, R t represents the t-th learning requirement vector, P tDenoted as the t-th proof of learning ability, a learning contract table is pre-maintained. This table divides learning behavior values into several intervals and configures corresponding contract templates for each interval, including learning objectives, progress requirements, assessment methods, and incentive standards. The contract table is also uploaded to the blockchain in the form of a smart contract to ensure its immutability and auditability. According to the calculated learning behavior value, locate the behavior interval it belongs to, extract the corresponding contract template from the learning contract table, generate the final learning contract information, and deploy it to the blockchain network through a smart contract to complete the contract signing. Through vectorization technology, learning requirements and ability proofs are finely characterized, and multi-dimensional matching ensures that the contract content is highly personalized to meet the different needs of different learners. All original data, the vectorization process, the contract table, and the final contract are uploaded to the blockchain for evidence storage, and any party can trace and verify them to enhance the credibility.

[0093] In a preferred embodiment, the steps of obtaining the co-learning protocol information according to the teaching content data and evaluation standard data of the tutor node include:

[0094] S301. Obtain the teaching content data and evaluation standard data of the tutor node;

[0095] S302. Obtain the corresponding teaching content matrix according to the teaching content data, and obtain a plurality of corresponding teaching content vectors according to the teaching content matrix;

[0096] S303. Obtain the corresponding evaluation standard matrix according to the evaluation standard data, and obtain a plurality of corresponding evaluation standard vectors according to the evaluation standard matrix;

[0097] S304. Obtain the historical teaching behavior data of the tutor node, and obtain the corresponding historical teaching feedback according to the historical teaching behavior data;

[0098] S305. Obtain the teaching quality value according to the plurality of teaching content vectors, the plurality of evaluation standard vectors, and the historical teaching feedback;

[0099] S306. Obtain the co-learning protocol table, where the co-learning protocol table includes a plurality of teaching quality intervals and the co-learning protocol information corresponding to each teaching quality interval;

[0100] S307. Obtain the corresponding co-learning protocol information from the co-learning protocol table according to the teaching quality interval corresponding to the teaching quality value.

[0101] In the above steps S301 to S307, two types of data are collected from the tutor node: teaching content data includes syllabus, courseware, video resources, exercise questions, etc., and evaluation standard data includes scoring rules, passing lines, excellent standards, feedback indicators, etc. These data are encrypted and stored on the chain. The teaching content data is mapped to a high-dimensional feature space. The rows of the matrix can represent knowledge point categories, difficulty levels, resource types (video / text / exercise questions), etc., and the columns are corresponding numerical values or codes. A dimensionality reduction or embedding algorithm (such as TF-IDF + PCA, deep learning encoder, etc.) is used to transform the matrix into multiple low-dimensional vectors. Each vector represents a type of teaching module or knowledge point set. The evaluation standard data is mapped to another high-dimensional feature space. The rows can include scoring dimensions (correct rate, innovation degree, completion degree, etc.), weight allocation, feedback timeliness, etc., and the columns are specific numerical values. Similar embedding or dimensionality reduction techniques as those for teaching content are used to obtain evaluation standard vectors corresponding one-to-one to each teaching content vector to ensure comprehensive evaluation in the same vector space. Query the historical teaching behavior data of the tutor node, including student scores, completion rates, interaction times, learning outcome quality, etc. of previous courses. Based on these original records, calculate and extract historical teaching feedback indicators, such as average satisfaction, deviation of course completion duration, response speed to questions, etc. Combine the "teaching content vector" with the "evaluation standard vector", and introduce historical teaching feedback to calculate the corresponding teaching quality value. The calculation formula of the teaching quality value is where W represents the teaching quality value, i represents the number of multiple teaching content vectors, i = 1, 2, 3...n, Q i represents the i-th teaching content vector, j represents the number of multiple evaluation standard vectors, j = 1, 2, 3...h, N j represents the j-th evaluation standard vector, G represents historical teaching feedback. Extract a co-learning protocol table, divide the teaching quality value into several intervals, and preset corresponding protocol templates for each interval, including teacher-student interaction frequency, assessment strictness, incentive mechanism, etc. The co-learning protocol table is stored on the chain in the form of a smart contract to ensure the transparency and immutability of the protocol terms. According to the calculated teaching quality value, determine the quality interval it belongs to, extract the co-learning protocol information corresponding to this interval from the co-learning protocol table, and deploy the protocol content to the blockchain network through the smart contract to complete the protocol signing and execution. Based on historical feedback and real-time quality calculation, dynamically select the protocol template, which can automatically adjust the protocol terms according to the actual performance of the tutor, enhancing flexibility.

[0102] In a preferred embodiment, the steps of obtaining the historical teaching behavior data of the tutor node and obtaining the corresponding historical teaching feedback according to the historical teaching behavior data include:

[0103] S3041. Obtain the historical teaching behavior data of the tutor node;

[0104] S3042, obtaining a corresponding history teaching behavior matrix according to the history teaching behavior data, and obtaining a corresponding plurality of history teaching behavior vectors according to the history teaching behavior matrix;

[0105] S3043, obtaining corresponding history teaching values according to multiple history teaching behavior vectors;

[0106] S3044, obtaining a history teaching table, wherein the history teaching table includes multiple history teaching intervals and history teaching feedback corresponding to each history teaching interval;

[0107] S3045. Obtain corresponding history teaching feedback from the history teaching table according to the history teaching interval corresponding to the history teaching value.

[0108] As in the above steps S3041 to S3045, the teaching interaction records of the tutor node are extracted from the on-chain or distributed storage of the tutor node, including multi-dimensional original behavior data such as the duration of classroom live broadcast, the number of homework corrections, the number of Q&A times, the student evaluation scores, and the course completion rate, to construct a historical teaching behavior matrix: the above original behavior data is mapped to a high-dimensional matrix, where rows represent different behavior dimensions (such as interaction frequency, homework timeliness, satisfaction score, etc.), and columns are specific numerical values or standardized indicators. Through dimensionality reduction or embedding algorithms (such as autoencoders, factor decomposition machines, etc.), the matrix is converted into multiple low-dimensional vectors, each vector represents the behavioral characteristics of the tutor in a certain historical time period or a certain type of teaching activity. The evaluation model is applied to multiple historical teaching behavior vectors to calculate the corresponding historical teaching value. The calculation formula of the historical teaching value is: Where L represents the historical teaching value, r represents the number of multiple historical teaching behavior vectors, r = 1, 2, 3…f, T r It is represented as the rth history teaching behavior vector, extracts a history teaching table, divides the history teaching value into several intervals, and presets corresponding history teaching feedback content for each interval, such as "interaction frequency needs to be improved", "maintain high-quality Q&A", "excellent teaching effect, and advanced courses can be recommended", etc. The table is also chained in the form of a smart contract to ensure that the interval division and feedback content are transparent and cannot be tampered with. According to the calculated history teaching value, the interval to which it belongs is located, and the history teaching feedback corresponding to the interval is extracted from the history teaching table. The feedback information is provided to the co-learning agreement generation module for dynamically adjusting the terms of the agreement or incentive strategy. Through multi-dimensional behavior data and vectorized models, the tutor's historical performance is quantified to achieve objective feedback based on real teaching behavior. The history teaching feedback can be updated in real time to help tutors improve teaching methods and interaction strategies in a targeted manner, forming a closed-loop improvement mechanism.

[0109] In a preferred embodiment, the step of obtaining the historical teaching behavior data of the tutor node includes:

[0110] S30411. Obtain teaching behavior values based on multiple teaching content vectors and multiple evaluation criterion vectors;

[0111] S30412. Obtain a teaching behavior table, where the teaching behavior table includes multiple teaching behavior intervals and the corresponding historical teaching duration for each teaching behavior interval;

[0112] S30413. Obtain the corresponding historical teaching duration from the teaching behavior table according to the teaching behavior interval corresponding to the teaching behavior value;

[0113] S30414. Collect the acquisition time node of the learning contract information and mark it as the end time of the historical teaching period;

[0114] S30415. Obtain the start time of the historical teaching period according to the historical teaching duration and the end time of the historical teaching period, and construct the historical teaching period;

[0115] S30416. Obtain historical teaching behavior data within the historical teaching period.

[0116] In the above steps S30411 to S30416, using the extracted teaching content vectors and evaluation criterion vectors, calculate and generate the corresponding teaching behavior values. The calculation formula for the teaching behavior values is In the formula, W represents the teaching behavior value, i represents the number of multiple teaching content vectors, i = 1, 2, 3... n, Q i represents the i-th teaching content vector, j represents the number of multiple evaluation criterion vectors, j = 1, 2, 3... h, N j represents the j-th evaluation criterion vector. Preset a teaching behavior table, divide the teaching behavior values into several intervals, and configure the corresponding historical teaching duration standards for each interval (such as low input corresponding to short duration, high input corresponding to long duration). The teaching behavior table is chained in the form of a smart contract to ensure the transparency and immutability of the interval division and duration standards. According to the calculated teaching behavior value, determine the interval where it is located, and extract the historical teaching duration corresponding to this interval from the teaching behavior table as the expected teaching duration of this teaching activity cycle. Record the time node of obtaining the learning contract information as the end timestamp of the historical teaching period. Based on the end time and historical teaching duration, calculate backward to obtain the start time of the historical teaching period, and combine the start time and the end time to construct a complete historical teaching period interval. Within this historical teaching period interval, extract all the teaching behavior records of this tutor from the chain or distributed storage, including classroom interaction, homework grading, question answering records, etc., to form a complete historical teaching behavior data set. Dynamically determine the duration based on the teaching behavior value, automatically divide the historical teaching period, avoid data deviation caused by fixed time periods, and more accurately reflect the tutor's real teaching activities.

[0117] In a preferred embodiment, the steps of obtaining interaction data, learning outcome data, and evaluation record data of a verification node and obtaining consensus information based on the interaction data, learning outcome data, and evaluation record data include:

[0118] S401. Obtain the interaction data, learning outcome data, and evaluation record data of the verification node;

[0119] S402. Obtain a corresponding interaction matrix according to the interaction data, and obtain a corresponding plurality of interaction vectors according to the interaction matrix;

[0120] S403. Obtain a corresponding learning outcome matrix according to the learning outcome data, and obtain a corresponding plurality of learning outcome vectors according to the learning outcome matrix;

[0121] S404. Obtain a corresponding evaluation record matrix according to the evaluation record data, and obtain a corresponding plurality of evaluation record vectors according to the evaluation record matrix;

[0122] S405. Obtain a consensus value according to the plurality of interaction vectors, the plurality of learning outcome vectors, and the plurality of evaluation record vectors;

[0123] S406. Obtain a consensus standard value, and obtain consensus information according to the consensus value.

[0124] In the above steps S401 to S406, three types of on-chain or distributed storage data are collected from the verification node: interaction data, such as Q&A records, discussion posts, and real-time interaction logs between learners and tutors; learning outcome data, such as test scores, project reports, and homework submission and grading results; evaluation record data, such as tutor evaluations, peer evaluations, and third-party review opinions. Through encryption and authorization mechanisms, the data sources are ensured to be reliable and tamper-proof. The interaction data is mapped to a high-dimensional feature space, where the rows can represent interaction frequencies, response durations, interaction quality scores, etc., and the columns are specific values. Dimensionality reduction or embedding algorithms (such as graph neural networks, Word2Vec, etc.) are applied to transform the matrix into multiple low-dimensional vectors, and each vector represents an interaction mode or stage. Achievement indicators such as scores, report quality, and submission timeliness rates are mapped to another high-dimensional matrix, and dimensionality reduction techniques (such as PCA, autoencoders) are used to generate multiple low-dimensional vectors, with each vector corresponding to a type of achievement performance. Evaluation scores, evaluation dimensions (depth, innovation, integrity), and evaluator identities are mapped to a high-dimensional space, and embedding or dimensionality reduction methods (such as factorization machines) are used to generate multiple low-dimensional vectors to characterize the evaluation record features. According to all the interaction vectors, achievement vectors, and evaluation vectors, a comprehensive consensus value is calculated. The calculation formula of the consensus value is In the formula, G present represents the consensus value, g represents the number of the plurality of interaction vectors, g = 1, 2, 3... m, J gDenoted as the g-th interaction vector, v denotes the number of multiple learning outcome vectors, v = 1, 2, 3... q, C v Denoted as the v-th learning outcome vector, b denotes the number of multiple evaluation record vectors, b = 1, 2, 3... a, K b Denoted as the b-th evaluation record vector. One or more consensus standard value thresholds are set in advance to determine different consensus levels. The calculated consensus value is compared with the standard value to generate corresponding consensus information, such as "highly consistent", "moderately consistent" or "needs further verification", etc., and is published on the blockchain through a smart contract. Combining the three types of data of interaction, outcome and evaluation, comprehensively evaluate the learning process and outcome, avoid single-dimensional deviation, improve the objectivity of consensus determination, and the vectorization and fusion model can be updated in real time to support fine-grained consensus level division, providing flexible support for trust decisions in different scenarios.

[0125] In a preferred embodiment, the steps of obtaining the consensus standard value and obtaining the consensus information according to the consensus value include:

[0126] S4061. Obtain the consensus standard value;

[0127] S4062. Obtain the consensus coefficient according to the consensus standard value and the consensus value;

[0128] S4063. Obtain the consensus table, where the consensus table includes multiple consensus coefficient intervals and the consensus information corresponding to each consensus coefficient interval;

[0129] S4064. Obtain the corresponding consensus coefficient from the consensus table according to the consensus coefficient interval corresponding to the consensus coefficient.

[0130] In the above steps S4061 to S4064, read the pre-set consensus standard value set from the on-chain smart contract or configuration storage. These standard values are usually set by network governance or administrators to divide different levels of consensus (for example, high consistency, medium consistency, low consistency, etc.). Compare the calculated consensus value with the consensus standard value, and calculate a consensus coefficient through a normalization or piecewise mapping algorithm. The calculation formula of the consensus coefficient is In the formula, G coefficient Denoted as the consensus coefficient, G standard Denoted as the consensus standard value, G presentIt is expressed as a consensus value and a consensus table is extracted. The table divides the consensus coefficient into several intervals and configures corresponding consensus information for each interval, such as "need to strengthen verification", "reach basic consensus", "high consensus, automatic pass", etc. The consensus table is uploaded to the chain in the form of a smart contract to ensure that each node can share and audit the content of the table. According to the calculated consensus coefficient, its interval in the consensus table is located, and the consensus information corresponding to the interval is extracted from the consensus table. The participants are notified through on-chain events or messages to guide subsequent teaching incentives or review processes. The consensus standard value and the consensus table are both uploaded to the chain for evidence to ensure that the consensus judgment standard is open, transparent and auditable, and to avoid inconsistent standards or secret operations between different nodes.

[0131] In a preferred embodiment, the steps of obtaining an incentive strategy based on the learning contract information, the co-learning agreement information and the consensus information, and obtaining a co-learning behavior reward based on the incentive strategy include:

[0132] S501, obtaining corresponding learning behavior values, teaching quality values and consensus values according to learning contract information, co-learning agreement information and consensus information;

[0133] S502, obtaining an incentive value according to the learning behavior value, the teaching quality value and the consensus value;

[0134] S503, obtaining an incentive table, wherein the incentive table includes multiple incentive value intervals and incentive rewards corresponding to each incentive value interval;

[0135] S504, obtaining a corresponding incentive reward from an incentive table according to an incentive value interval corresponding to the incentive value;

[0136] S505. Obtain a reward for co-learning behavior based on the incentive reward.

[0137] As in the above steps S501 to S505, the pre-calculated learning behavior value is read from the learning contract information, the corresponding teaching quality value is read from the co-learning agreement information, and the consensus value is read from the consensus information. The above three types of values are calculated to obtain a comprehensive incentive value. The calculation formula of the incentive value is F = L·W·G present , where F represents the incentive value, L represents the learning behavior value, W represents the teaching quality value, and G presentIt is expressed as a consensus value. The incentive value quantitatively represents the comprehensive level of contribution and effect of all parties in this co-learning activity. An incentive table is extracted to divide the incentive value into several intervals, and corresponding incentive rewards are preset for each interval, such as the number of tokens, points or other incentive means. The incentive table is chained in the form of a smart contract to ensure that the reward rules are open, transparent and cannot be tampered with. According to the calculated incentive value, the interval to which it belongs is determined, and the incentive reward corresponding to the interval is extracted from the incentive table to determine the type and amount of rewards that learners, mentors and verification nodes should receive. According to the content of the incentive reward, the smart contract automatically distributes the corresponding tokens or points to the wallets or accounts of each participating node, and notifies the learners, mentors and verification nodes through on-chain events to complete the entire reward distribution process. The three indicators of learning completion, teaching quality and multi-party consensus are integrated to build a comprehensive and fair incentive model to avoid bias in a single dimension. The incentive table and reward rules are chained and stored. Any participant can audit the incentive value calculation process and reward distribution results. The incentive model and table can be adjusted in real time according to the network scale, teaching needs or community governance to maintain the flexibility and adaptability of the incentive mechanism.

[0138] Please refer to the attached Figure 2 As shown, the present invention also provides a blockchain-based mutual assistance and co-learning education system, which is used for the above-mentioned blockchain-based mutual assistance and co-learning education method, including:

[0139] A blockchain module, used to obtain a decentralized education mutual aid blockchain network, wherein the education mutual aid blockchain network includes learner nodes, tutor nodes, and verification nodes;

[0140] The learning contract module is used to obtain the learning demand data and learning ability proof data of the learner node, and obtain the learning contract information based on the learning demand data and learning ability proof data;

[0141] The co-learning agreement module is used to obtain the teaching content data and evaluation standard data of the tutor node, and obtain the co-learning agreement information based on the teaching content data and evaluation standard data;

[0142] The consensus module is used to obtain the interaction data, learning achievement data and evaluation record data of the verification node, and obtain consensus information based on the interaction data, learning achievement data and evaluation record data;

[0143] The co-learning reward module is used to obtain incentive strategies based on learning contract information, co-learning agreement information and consensus information, and obtain co-learning behavior rewards based on the incentive strategies.

[0144] As described above, the blockchain module deploys and maintains a decentralized educational mutual-aid blockchain network, including learner nodes, tutor nodes, and verification nodes. The learning contract module collects the learning requirement data and proof-of-ability data of the learner nodes, vectorizes the learning requirements and proof of ability, calculates the learning behavior value, queries the predefined learning contract table, matches the contract template according to the behavior value range, and uploads the final learning contract to the chain through a smart contract, clarifying the learning objectives, assessment indicators, and incentive rules, and generating and deploying the corresponding "learning contract information". The co-learning protocol module collects the teaching content and evaluation standard data of the tutor nodes, vectorizes the teaching content and evaluation standards, calculates the teaching quality value in combination with historical teaching feedback, queries the co-learning protocol table, matches the protocol template according to the quality value range, and uploads the protocol to the chain through a smart contract, clarifying the teaching process, evaluation method, and the rights and responsibilities of both parties, and generating the "co-learning protocol information". The consensus module collects the interaction data, learning achievement data, and evaluation records of the verification nodes, vectorizes the three types of data of interaction, achievement, and evaluation respectively, calculates the consensus value through multi-modal fusion, maps it to a consensus coefficient with the standard value, obtains the corresponding consensus information from the consensus table according to the consensus coefficient, uploads it to the chain and publishes it to all parties, and generates the "consensus information". The incentive reward module extracts the learning behavior value, teaching quality value, and consensus value, calculates the comprehensive incentive value through fusion, queries the incentive table, matches the incentive reward according to the incentive value range, and the smart contract automatically distributes token or point rewards to learners, tutors, and verification nodes and records them on the chain. The whole process (data collection, evaluation, contract signing, incentive distribution) is executed based on the blockchain smart contract, all rules and records are uploaded to the chain for evidence storage, and any node can conduct audits to prevent fraud and black-box operations. Equal emphasis is placed on learning behavior, teaching quality, and consensus degree to build a comprehensive incentive system, which can not only encourage learners to study actively but also motivate tutors to provide high-quality teaching, while ensuring the fair review of verification nodes.

[0145] And, a mutual-aid co-learning educational terminal based on blockchain, comprising:

[0146] One or more processors;

[0147] A storage device having one or more programs stored thereon;

[0148] When the one or more programs are executed by the one or more processors, the one or more processors implement the mutual-aid co-learning educational method based on blockchain.

[0149] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art in the technical field of the present invention, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. The structures, devices, and operation methods not specifically described and explained in the present invention, unless otherwise specified and limited, are implemented according to the conventional means in the art.

Claims

1. A mutual-aid and co-learning education method based on blockchain, characterized in that Including: Obtain a decentralized educational mutual-aid blockchain network, where the educational mutual-aid blockchain network includes learner nodes, tutor nodes, and verification nodes; Obtain the learning demand data and learning ability proof data of the learner nodes, and obtain learning contract information based on the learning demand data and learning ability proof data; Obtain the teaching content data and evaluation standard data of the tutor nodes, and obtain co-learning protocol information based on the teaching content data and evaluation standard data; Obtain the interaction data, learning achievement data, and evaluation record data of the verification nodes, and obtain consensus information based on the interaction data, learning achievement data, and evaluation record data; Obtain an incentive strategy based on the learning contract information, co-learning protocol information, and consensus information, and obtain co-learning behavior rewards based on the incentive strategy.

2. The mutual learning education method based on blockchain according to claim 1, wherein The steps of obtaining the learning demand data and learning ability proof data of the learner nodes, and obtaining learning contract information based on the learning demand data and learning ability proof data include: Obtain the learning demand data and learning ability proof data of the learner nodes; Obtain the corresponding learning demand matrix according to the learning demand data, and obtain multiple corresponding learning demand vectors according to the learning demand matrix; Obtain the corresponding learning ability proof matrix according to the learning ability proof data, and obtain the learning ability proof vectors corresponding to each learning demand vector according to the learning ability proof matrix; Obtain learning behavior values according to the multiple learning demand vectors and multiple learning ability proof vectors; Obtain a learning contract table, where the learning contract table includes multiple learning behavior intervals and the learning contract information corresponding to each learning behavior interval; Obtain the corresponding learning contract information from the learning contract table according to the learning behavior interval corresponding to the learning behavior value.

3. The mutual-aid and co-study education method based on blockchain according to claim 1, characterized in that, The steps of obtaining the teaching content data and evaluation standard data of the tutor nodes, and obtaining co-learning protocol information based on the teaching content data and evaluation standard data include: Obtain the teaching content data and evaluation standard data of the tutor nodes; Obtain the corresponding teaching content matrix according to the teaching content data, and obtain multiple corresponding teaching content vectors according to the teaching content matrix; Obtain the corresponding evaluation standard matrix according to the evaluation standard data, and obtain multiple corresponding evaluation standard vectors according to the evaluation standard matrix; Obtain the historical teaching behavior data of the tutor nodes, and obtain the corresponding historical teaching feedback according to the historical teaching behavior data; Obtain teaching quality values according to the multiple teaching content vectors, multiple evaluation standard vectors, and historical teaching feedback; Obtain a co-learning protocol table, where the co-learning protocol table includes multiple teaching quality intervals and the co-learning protocol information corresponding to each teaching quality interval; Obtain the corresponding co-learning protocol information from the co-learning protocol table according to the teaching quality interval corresponding to the teaching quality value.

4. The mutual-aid and co-study education method based on blockchain according to claim 3, characterized in that, The steps of obtaining the historical teaching behavior data of the tutor nodes, and obtaining the corresponding historical teaching feedback according to the historical teaching behavior data include: Obtain the historical teaching behavior data of the tutor nodes; Obtain the corresponding historical teaching behavior matrix according to the historical teaching behavior data, and obtain multiple corresponding historical teaching behavior vectors according to the historical teaching behavior matrix; Obtain the corresponding historical teaching values according to the multiple historical teaching behavior vectors; Obtain a historical teaching table, where the historical teaching table includes multiple historical teaching intervals and the corresponding historical teaching feedback for each historical teaching interval; Obtain the corresponding historical teaching feedback from the historical teaching table according to the historical teaching interval corresponding to the historical teaching value.

5. The mutual learning education method based on blockchain according to claim 4, wherein, Steps for obtaining the historical teaching behavior data of the tutor node, including: Obtain teaching behavior values according to multiple teaching content vectors and multiple evaluation criterion vectors; Obtain a teaching behavior table, where the teaching behavior table includes multiple teaching behavior intervals and the corresponding historical teaching duration for each teaching behavior interval; Obtain the corresponding historical teaching duration from the teaching behavior table according to the teaching behavior interval corresponding to the teaching behavior value; Collect the acquisition time node of the learning contract information and mark it as the end time of the historical teaching period; Obtain the start time of the historical teaching period according to the historical teaching duration and the end time of the historical teaching period, and construct the historical teaching period; Obtain the historical teaching behavior data within the historical teaching period.

6. The blockchain-based mutual learning education method according to claim 1, characterized in that Steps for obtaining the interaction data, learning achievement data, and evaluation record data of the verification node, and obtaining consensus information according to the interaction data, learning achievement data, and evaluation record data, including: Obtain the interaction data, learning achievement data, and evaluation record data of the verification node; Obtain the corresponding interaction matrix according to the interaction data, and obtain the corresponding multiple interaction vectors according to the interaction matrix; Obtain the corresponding learning achievement matrix according to the learning achievement data of this learning, and obtain the corresponding multiple learning achievement vectors according to the learning achievement matrix; Obtain the corresponding evaluation record matrix according to the evaluation record data, and obtain the corresponding multiple evaluation record vectors according to the evaluation record matrix; Obtain a consensus value according to multiple interaction vectors, multiple learning achievement vectors, and multiple evaluation record vectors; Obtain a consensus standard value, and obtain consensus information according to the consensus value.

7. The mutual learning education method based on blockchain according to claim 6, wherein Steps for obtaining a consensus standard value and obtaining consensus information according to the consensus value, including: Obtain a consensus standard value; Obtain a consensus coefficient according to the consensus standard value and the consensus value; Obtain a consensus table, where the consensus table includes multiple consensus coefficient intervals and the corresponding consensus information for each consensus coefficient interval; Obtain the corresponding consensus coefficient from the consensus table according to the consensus coefficient interval corresponding to the consensus coefficient.

8. The blockchain-based mutual learning education method according to claim 1, characterized in that, Steps for obtaining an incentive strategy according to the learning contract information, co-learning agreement information, and consensus information, and obtaining co-learning behavior rewards according to the incentive strategy, including: Obtain the corresponding learning behavior value, teaching quality value, and consensus value according to the learning contract information, co-learning agreement information, and consensus information respectively; Obtain an incentive value according to the learning behavior value, teaching quality value, and consensus value; Obtain an incentive table, where the incentive table includes multiple incentive value intervals and the corresponding incentive rewards for each incentive value interval; Obtain the corresponding incentive reward from the incentive table according to the incentive value interval corresponding to the incentive value; Obtain co-learning behavior rewards according to the incentive rewards.

9. A blockchain-based mutual assistance and co-learning education system, which is applied to the blockchain-based mutual assistance and co-learning education method described in any one of claims 1 to 8, and is characterized in that, Include: A blockchain module for obtaining a decentralized educational mutual assistance blockchain network, where the educational mutual assistance blockchain network includes learner nodes, tutor nodes, and verification nodes; A learning contract module, configured to obtain learning requirement data and learning ability proof data of a learner node, and obtain learning contract information according to the learning requirement data and the learning ability proof data; A co-learning protocol module, configured to obtain teaching content data and evaluation criterion data of a tutor node, and obtain co-learning protocol information according to the teaching content data and the evaluation criterion data; A consensus module, configured to obtain interaction data, learning achievement data and evaluation record data of a verification node, and obtain consensus information according to the interaction data, the learning achievement data and the evaluation record data; A co-learning reward module, configured to obtain an incentive strategy according to the learning contract information, the co-learning protocol information and the consensus information, and obtain co-learning behavior rewards according to the incentive strategy.

10. A mutual-aid and co-study education terminal based on blockchain, characterized in that, Including: One or more processors; A storage device storing one or more programs thereon; When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the blockchain-based mutual co-learning education method according to any one of claims 1 to 8.

Images