Credit bank full-nano learning achievement-oriented credit general exchange and consensus construction method and credit bank full-nano learning achievement-oriented credit general exchange and consensus construction system

Abstract

The invention, which relates to the technical field of learning achievement authentication, discloses a credit general exchange and consensus construction method for credit bank full-nano learning achievements, comprising a full-nano learning achievement uplink request module, a full-nano learning achievement digital tag module, a full-nano learning achievement evaluation module, and a consensus result output and feedback module. The learning achievement request uplink comprises the following contents: learning achievement request uplink refers to an educational education learning achievement, a corresponding credit obtained by completing related courses during a school period and an educational certificate after graduation, and meanwhile, the learning achievement request uplink comprises a non-educational learning achievement, various technical grade certificates and a learning achievement without a fixed form; according to the scheme, the learning achievement is authenticated by adopting a multi-person authentication algorithm, the input person modifies and inputs the learning achievement, after the input is completed, the input person applies for learning achievement authentication, and then authentication is carried out to judge whether the input or modified learning achievement accords with the input or modified learning achievement; if yes, uploading the result to a learning result chain and storing and updating the result, and if not, returning the result.

Description

Technical Field

[0001] The present invention relates to the field of intelligent algorithms, and in particular to a credit exchange and consensus building method and system for inclusive learning outcomes of a credit bank. Background Art

[0002] With the rapid development of digital technology and the transformation of global education models, the traceability, verifiability and transparency of learning outcomes are becoming increasingly important. This can not only effectively prevent academic misconduct such as plagiarism and forgery, but also provide educators and learners with more accurate and comprehensive learning assessments. In this context, the Learning Outcome Chain based on blockchain technology has gradually attracted attention.

[0003] Blockchain technology, with its decentralized and tamper-proof characteristics, provides a technical basis for the authentication and traceability of learning outcomes. Through blockchain, learners' learning outcomes can be effectively recorded and verified, thus building a reliable and transparent learning outcomes chain.

[0004] However, most of the current blockchain-based learning achievement chain construction methods focus on a single certification agency or centralized certification, which limits its application scope and credibility to a certain extent. Therefore, how to build an inclusive learning achievement chain based on a multi-person certification algorithm to improve its decentralization and credibility has become a problem that needs to be solved urgently. Summary of the invention

[0005] The main purpose of the present invention is to solve the problem that most of the existing blockchain-based learning achievement chain construction methods focus on a single certification agency or centralized certification, which to a certain extent limits its scope of application and credibility. A credit exchange and consensus construction method for inclusive learning outcomes of credit banks is provided, including the following steps:

[0006] The step of requesting inclusive learning outcomes to be uploaded to the blockchain is to collect inclusive learning outcomes and upload them to the blockchain; the step of digital labeling is to assign digital labels to each learning outcome, and the digital labels include digital labels for academic education certificates, digital labels for professional qualification certificates, digital labels for social evaluation certificates, and digital labels for expert information; the step of credit redemption for inclusive learning outcomes is to screen evaluation experts based on the maximum entropy model to achieve credit conversion and mutual recognition between different learning outcomes.

[0007] The steps of requesting to upload inclusive learning results to the blockchain include:

[0008] Preprocessing of inclusive learning outcomes; including processing of images and explanatory texts of three types of outcomes, namely academic education certificates, professional qualification certificates and social training certificates, and generating personal private keys before uploading to the chain; request for uploading of inclusive learning outcomes to the chain; uploading of learning outcome images and explanatory texts encrypted with personal private keys, and issuing a request for uploading learning outcomes to the chain; the system determines whether the accuracy rate is greater than the threshold. When the accuracy rate is less than the threshold, the learning outcome request to be uploaded to the chain is returned as an error message, and when the accuracy rate is greater than or equal to the threshold, the learning outcome is uploaded to the chain to obtain block information; the server receives the request for uploading the learning outcome to the chain, decrypts and verifies it, and gives a response of whether the verification is passed or not. The blockchain is built by the Fabric solution, including member management service, blockchain service, chain code service and events. The member management service is responsible for managing the node identity and authority in the network to ensure the security and credibility of the network. The blockchain service provides consensus management, distributed ledger implementation, ledger storage and communication between nodes in the network for the main functions of the blockchain. The chain code service provides the required environment for the deployment and operation of the chain code. The chain code is a smart contract in Fabric, which defines the transaction logic between nodes in the network. The event provides technical implementation for asynchronous communication between components. In Fabric, the event mechanism allows different components to communicate and collaborate through events without direct interaction.

[0009] The digital labeling step comprises:

[0010] Digital labels for academic education certificates: Based on the uploaded academic education pictures and explanatory texts, words are extracted to form the digital labels for academic education certificates, including school name, academic level, major, and graduation year; Digital labels for professional qualification certificates: Based on the uploaded professional qualification pictures and explanatory texts, words are extracted to form the digital labels for professional qualification certificates, including certificate name, issuing department, and issuing date; Digital labels for social evaluation certificates: Based on the uploaded social evaluation certificate pictures and explanatory texts, words are extracted to form the digital labels for social evaluation certificates, including issuing department and certificate category; Digital labels for expert information: Based on the expert's self-introduction text, words are extracted to form the digital labels for expert information, including the fields of artificial intelligence, education, transportation and logistics, finance, and medical health.

[0011] The steps for credit redemption for inclusive learning outcomes include:

[0012] Evaluation expert selection based on the maximum entropy model: The text of the evaluation expert and the text of the learning outcome description are matched through the maximum entropy model, and the three experts with the highest matching degree are selected to evaluate the uploaded learning outcomes. The maximum entropy model is described as follows:

[0013] Assume that the set of models that satisfy all constraints is:

[0014]

[0015] The conditional entropy defined on the conditional probability distribution P(Y|X) is:

[0016]

[0017] Then the model with the largest conditional entropy H(P) in the model set C is called the maximum entropy model;

[0018] Learning achievement credit exchange system: including learning achievement levels, credit exchange principles and conversion relationships. The conversion adopts a standardized form, and the formula is:

[0019]

[0020] Value refers to the standardized credit value, V now Refers to the original credit value, V min is the minimum value of this type of learning outcome, and Vmax is the maximum value of this type of learning outcome;

[0021] Credit recognition for learning outcomes: Experts will recognize the credits of the uploaded outcomes based on the credit exchange system. Each outcome is determined by averaging the credits given by three experts.

[0022] The method also includes a consensus building method:

[0023] On-chain release of credits: After the experts complete the credit assessment, the system uploads it to the blockchain, and the credits are released on the chain after background review; consensus of results: enterprises and users on the blockchain reach a consensus on the previous credit exchange results; feedback on results: consensus on the inclusive learning outcomes of the credit bank is completed and feedback is provided.

[0024] The present invention also provides a credit exchange and consensus building system for inclusive learning outcomes in a credit bank, including an inclusive learning outcome chain request module, a digital label module and an inclusive learning outcome credit exchange module. The inclusive learning outcome chain request module is used to collect inclusive learning outcomes and upload them to the blockchain; the digital label module assigns a digital label to each learning outcome; the inclusive learning outcome credit exchange module realizes credit conversion and mutual recognition between different learning outcomes through evaluation expert screening based on the maximum entropy model.

[0025] The excellent effects of the present invention are:

[0026] The present invention reduces the reliance on a single certification body by introducing a multi-person certification algorithm, thereby enhancing the decentralization of the learning achievement chain. This means that there is no single centralized control point, which improves the stability and reliability of the system.

[0027] Since this method combines the certification results of multiple certification bodies or individuals, it can provide a more comprehensive and accurate certification of learning outcomes. This comprehensive certification method reduces the bias or error that may be caused by a single certification, thereby improving the credibility of the learning outcomes chain.

[0028] The inclusive learning achievement chain of the present invention records all the learning achievements of learners and their corresponding certification information, ensuring the integrity and traceability of the data. This enables educators and learners to more accurately evaluate the learning process and learning achievements. In the process of constructing the inclusive learning achievement chain, the method ensures the security and privacy protection of data through encryption technology and access control. This helps to maintain the security of learners' personal information and academic achievements and prevent data leakage and abuse. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of the inclusive learning outcomes chain.

[0030] Figure 2 This is a schematic diagram of the inclusive learning outcomes chain modules.

[0031] in:

[0032] The inclusive learning achievement chain request module 1 includes learning achievement preprocessing 2, chain request 3 and chain response 4, digital label module 5, digital label of academic education certificate 6, digital label of professional qualification certificate 7, digital label of social evaluation certificate 8, digital label of expert information 9, inclusive learning achievement credit exchange module 10, evaluation expert screening based on maximum entropy model 11, learning achievement credit exchange system 12, learning achievement credit recognition 13, consensus building module 14, chain release of credits 15, consensus of results 16, and feedback of results 17. DETAILED DESCRIPTION

[0033] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] The four core components of Fabric include:

[0035] Membership Service:

[0036] Function: Responsible for managing node identities and permissions in the network to ensure the security and credibility of the network. Member services provide member registration, management and audit functions to ensure the security of access to the Hyperledger Fabric platform.

[0037] Features: Member services are usually integrated with existing authentication systems (such as LDAP, OAuth, etc.) to provide secure identity management capabilities.

[0038] Blockchain Service:

[0039] Function: The core part of blockchain services, providing underlying support for the main functions of blockchain, including consensus management, distributed ledger implementation, ledger storage, and communication between nodes in the network.

[0040] Features: Blockchain service is the core foundation of Fabric blockchain network, which consists of multiple nodes, each of which can be a client node, a verification node or a sorting node. These nodes together form a distributed, tamper-proof ledger, ensuring the security and transparency of data.

[0041] Chaincode Service:

[0042] Function: Provides the required environment for chaincode deployment and runtime. Chaincode is a smart contract in Fabric that defines the transaction logic between nodes in the network.

[0043] Features: Chaincode runs in a secure container and provides corresponding APIs to interact with ledger data. Chaincodes are usually written in languages ​​such as Go, JavaScript, or Java, and they define the management rules and transaction logic of assets in the network.

[0044] Events:

[0045] Function: Provides technical implementation for asynchronous communication between components. In Fabric, the event mechanism allows different components to communicate and collaborate through events without direct interaction.

[0046] Features: The event mechanism improves the flexibility and scalability of the Fabric system, enabling the system to better adapt to complex and changing business scenarios.

[0047] A credit exchange and consensus building method for inclusive learning outcomes in a credit bank, characterized in that the method comprises:

[0048] The step of requesting inclusive learning outcomes to be uploaded to the blockchain is to collect inclusive learning outcomes and upload them to the blockchain; the step of digital labeling is to assign digital labels to each learning outcome, and the digital labels include digital labels for academic education certificates, digital labels for professional qualification certificates, digital labels for social evaluation certificates, and digital labels for expert information; the step of credit redemption for inclusive learning outcomes is to screen evaluation experts based on the maximum entropy model to achieve credit conversion and mutual recognition between different learning outcomes.

[0049] Specifically, the following steps are included:

[0050] 1. Steps for requesting inclusive learning results to be uploaded to the blockchain

[0051] Data preparation:

[0052] Collect and organize data on inclusive learning outcomes, including academic education certificates, professional qualification certificates, social evaluation certificates, etc.

[0053] Clean and format data to ensure accuracy and consistency.

[0054] Choose a blockchain platform:

[0055] Choose a suitable blockchain platform according to your needs, such as Ethereum, Hyperledger, etc. These platforms provide rich development tools and community support.

[0056] Pre-chaining treatment:

[0057] Use SDK or related tools to serialize and sign data to ensure data security and non-tamperability.

[0058] According to the requirements of the blockchain platform, a transaction structure is constructed and the learning outcome data is placed in it.

[0059] Broadcasting a transaction:

[0060] Broadcast the transaction containing the learning outcome data to the blockchain network.

[0061] Wait for nodes in the network to verify and reach consensus on the transaction.

[0062] Storage and Verification:

[0063] Once the transaction is confirmed through the consensus algorithm, the learning outcome data will be permanently stored on the blockchain.

[0064] Any user who needs to verify the authenticity of learning outcomes can query and verify data from the blockchain.

[0065] 2. Digital label assignment steps

[0066] Define the tag specification:

[0067] Establish specifications for digital labels, including label format, content, and uniqueness requirements.

[0068] Determine label templates for different types of learning outcomes (such as academic education certificates, professional qualification certificates, etc.).

[0069] Generate tags:

[0070] Use encryption algorithms or hash functions to generate a unique digital label for each learning outcome.

[0071] Ensure that labels are closely associated with corresponding learning outcome data and are easy to query and verify.

[0072] Label allocation and binding:

[0073] Assign the generated digital labels to the corresponding learning outcomes.

[0074] The binding relationship between the label and the learning outcome data is recorded on the blockchain to ensure the uniqueness and traceability of the label.

[0075] Tag Management:

[0076] Establish a label management system for label generation, allocation, query and update.

[0077] Ensure the security and stability of the label management system to prevent labels from being tampered with or misused.

[0078] III. Steps for redeeming credits for inclusive learning outcomes

[0079] Formulate credit transfer rules:

[0080] Based on the maximum entropy model or other evaluation models, formulate credit conversion rules between different learning outcomes.

[0081] Invite experts in relevant fields to participate in the formulation and review of rules to ensure the fairness and rationality of the rules.

[0082] Credit transfer application:

[0083] The user submits a credit transfer application, including the digital labels of the source and target learning outcomes and related information.

[0084] The system automatically calculates the converted credit value according to the conversion rules and generates a conversion report.

[0085] Expert review:

[0086] For complex or controversial conversion applications, the system can invite evaluation experts to conduct manual review.

[0087] Experts review the application based on the conversion rules and actual conditions and give review opinions.

[0088] Credit recognition and issuance:

[0089] Once the credit conversion application is approved, the system will automatically update the user's credit record and issue the converted credits to the user.

[0090] Users can check their credit status in the system and conduct further study or certification as needed.

[0091] Through the above steps, inclusive learning outcomes can be safely and efficiently uploaded to the chain, assigned digital labels and credits can be redeemed, providing strong support for learners' lifelong learning and development.

[0092] As a preferred implementation, the step of requesting to upload inclusive learning results to the blockchain includes:

[0093] Preprocessing of inclusive learning results; including processing of images and explanatory texts of three types of results, namely, academic education certificates, professional qualification certificates and social training certificates, and generating personal private keys before uploading to the blockchain; request for uploading inclusive learning results; uploading learning results images and explanatory texts encrypted with personal private keys, and issuing a request for uploading learning results to the blockchain; the system determines whether the accuracy is greater than the threshold value based on the accuracy rate. When the accuracy rate is less than the threshold value, the learning results request for uploading to the blockchain is returned as an error message, and when the accuracy rate is greater than or equal to the threshold value, the learning results are uploaded to the blockchain to obtain block information. The server receives the request for uploading learning results to the blockchain, decrypts and verifies, and gives a response of whether the verification is passed or not.

[0094] In the above scheme, the learning results are preprocessed before being uploaded to the chain, including the cleaning and formatting of pictures and captions, which helps to reduce the failure of uploading to the chain or subsequent verification problems caused by data quality problems. The introduction of an accuracy judgment mechanism allows uploading to the chain only when the preprocessed data meets certain accuracy requirements, which greatly improves the accuracy and reliability of the uploading data. When the data accuracy is found to be lower than the threshold during the preprocessing or verification process, the uploading request can be automatically regarded as an error message and sent back for processing, avoiding invalid data from occupying blockchain resources and improving the efficiency and stability of the system. This automated error handling mechanism reduces the burden of manual review and also speeds up the feedback and resolution of problems.

[0095] As a preferred implementation, the digital labeling step includes:

[0096] Digital labels for academic education certificates: Based on the uploaded academic education pictures and explanatory texts, words are extracted to form the digital labels for academic education certificates, including school name, academic level, major, and graduation year; Digital labels for professional qualification certificates: Based on the uploaded professional qualification pictures and explanatory texts, words are extracted to form the digital labels for professional qualification certificates, including certificate name, issuing department, and issuing date; Digital labels for social evaluation certificates: Based on the uploaded social evaluation certificate pictures and explanatory texts, words are extracted to form the digital labels for social evaluation certificates, including issuing department and certificate category; Digital labels for expert information: Based on the expert's self-introduction text, words are extracted to form the digital labels for expert information, including the fields of artificial intelligence, education, transportation and logistics, finance, and medical health.

[0097] In the above scheme, by defining a unified digital label format and content, standardized processing of different types of learning outcomes and expert information is achieved. This facilitates data exchange and sharing between different systems and improves data interoperability. Standardized processing also makes data easier to query, retrieve and analyze, providing convenience for subsequent credit conversion, mutual recognition and other operations. By generating digital labels for various types of learning outcomes and expert information, this scheme provides strong support for the establishment of a lifelong learning system. It enables learners' learning outcomes to be accurately recorded, effectively managed and widely recognized, promoting the accumulation and inheritance of knowledge.

[0098] As a preferred implementation, the inclusive learning achievement credit redemption step includes:

[0099] Evaluation expert selection based on the maximum entropy model: The text of the evaluation expert and the text of the learning outcome description are matched through the maximum entropy model, and the three experts with the highest matching degree are selected to evaluate the uploaded learning outcomes. The maximum entropy model is described as follows:

[0100] Assume that the set of models that satisfy all constraints is:

[0101]

[0102] The conditional entropy defined on the conditional probability distribution P(Y|X) is:

[0103]

[0104] Then the model with the largest conditional entropy H(P) in the model set C is called the maximum entropy model;

[0105] Learning achievement credit exchange system: including learning achievement levels, credit exchange principles and conversion relationships. The conversion adopts a standardized form, and the formula is:

[0106]

[0107] Value refers to the standardized credit value, V now Refers to the original credit value, V min is the minimum value of this type of learning outcome, and Vmax is the maximum value of this type of learning outcome;

[0108] Credit recognition for learning outcomes: Experts will recognize the credits of the uploaded outcomes based on the credit exchange system. Each outcome is determined by averaging the credits given by three experts.

[0109] In the above scheme, the maximum entropy model is used to match the text of the evaluation experts and the text of the learning outcome description, which can accurately screen out the experts who are most relevant to the uploaded learning outcomes. This screening method based on text similarity effectively avoids the subjectivity and inefficiency of traditional manual screening, and improves the accuracy and efficiency of expert screening. The top three experts with the highest matching degree not only have the professional knowledge and evaluation ability of the learning outcome, but also can provide comprehensive and objective evaluation opinions from multiple angles, which enhances the fairness and credibility of credit recognition. A standardized credit exchange system has been established, including the level of learning outcomes, the principles of credit exchange and the conversion relationship. This standardized processing method enables learning outcomes from different sources and types to be compared and converted under the same framework, which makes it possible for mutual recognition and exchange of credits.

[0110] The above scheme effectively improves the accuracy, efficiency, fairness and reliability of credit exchange for inclusive learning outcomes by introducing an evaluation expert screening mechanism based on the maximum entropy model and a standardized credit exchange system, as well as adopting methods such as multi-expert evaluation and averaging processing, providing strong support for the digital transformation of the education field and the construction of a lifelong learning system.

[0111] As a preferred embodiment, the method further includes a consensus building method:

[0112] On-chain release of credits: After the experts complete the credit assessment, the system uploads it to the blockchain, and the credits are released on the chain after background review; consensus of results: enterprises and users on the blockchain reach a consensus on the previous credit exchange results; feedback on results: consensus on the inclusive learning outcomes of the credit bank is completed and feedback is provided.

[0113] Another embodiment of the present invention is a credit exchange and consensus building system, a credit exchange and consensus building system for inclusive learning outcomes of a credit bank, comprising an inclusive learning outcome chain request module, a digital label module and an inclusive learning outcome credit exchange module, wherein the inclusive learning outcome chain request module is used to collect inclusive learning outcomes and upload them to the blockchain; the digital label module assigns a digital label to each learning outcome, wherein the digital label includes a digital label for academic education certificates, a digital label for professional qualification certificates, a digital label for social evaluation certificates and a digital label for expert information; the inclusive learning outcome credit exchange module implements credit conversion and mutual recognition between different learning outcomes through evaluation expert screening based on a maximum entropy model.

[0114] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A credit exchange and consensus building method for inclusive learning outcomes in a credit bank, characterized by: The method comprises: The step of requesting inclusive learning results to be uploaded to the blockchain is to collect inclusive learning results and upload them to the blockchain. The blockchain is built based on the Fabric solution, including member management services, blockchain services, chain code services and events. The member management service is responsible for managing the node identities and permissions in the network to ensure the security and credibility of the network. The blockchain service provides consensus management, distributed ledger implementation, ledger storage and communication between nodes in the network for the main functions of the blockchain. The chain code service provides the required environment for the deployment and operation of the chain code. The chain code is a smart contract in Fabric that defines the transaction logic between nodes in the network. The event provides technical implementation for asynchronous communication between components. In Fabric, the event mechanism allows different components to communicate and collaborate through events without direct interaction. A digital labeling step, assigning a digital label to each learning outcome, wherein the digital label includes a digital label for academic education certificate, a digital label for professional qualification certificate, a digital label for social evaluation certificate, and a digital label for expert information; The credit redemption procedure for inclusive learning outcomes is based on the screening of evaluation experts based on the maximum entropy model to achieve credit conversion and mutual recognition between different learning outcomes.

2. According to claim 1, a credit exchange and consensus building method for inclusive learning outcomes of credit banks, characterized in that: The steps of requesting to upload inclusive learning results to the blockchain include: Pre-processing of inclusive learning outcomes, including processing of images and captions of three types of outcomes: academic education certificates, professional qualification certificates, and social training certificates, and generating personal private keys before uploading to the blockchain; Request to upload inclusive learning results to the blockchain; upload learning results pictures and explanatory text encrypted with personal private keys, and send a request to upload learning results to the blockchain; the system determines whether the accuracy rate is greater than the threshold. When the accuracy rate is less than the threshold, the learning results request to upload to the blockchain is rejected as an error message, and when the accuracy rate is greater than or equal to the threshold, the learning results are uploaded to the blockchain to obtain block information; The server receives the request to upload the learning results to the chain, decrypts and verifies it, and gives a response of whether the verification is passed or not.

3. A credit exchange and consensus building method for inclusive learning outcomes in a credit bank according to claim 2, characterized in that: The digital labeling step comprises: Digital labels for academic education certificates: Based on the uploaded academic education pictures and description texts, words are extracted from them to form digital labels for academic education certificates, including school name, academic level, major, and graduation year; Digital label of professional qualification certificate: based on the uploaded professional qualification picture and description text, extract words from them to form the digital label of professional qualification certificate, including certificate name, issuing department, and issuing date; Digital label of social evaluation certificate: according to the uploaded social evaluation certificate picture and description text, extract words from them to form the digital label of social evaluation certificate, including issuing department and certificate category; Digital labels for expert information: Based on the expert’s self-introduction text, words are extracted from it to form digital labels for expert information, including the fields of artificial intelligence, education, transportation and logistics, finance, and medical health.

4. A method for credit exchange and consensus building for inclusive learning outcomes in a credit bank according to claim 3, characterized in that: The steps for credit redemption for inclusive learning outcomes include: Evaluation expert selection based on the maximum entropy model: The text of the evaluation expert and the text of the learning outcome description are matched through the maximum entropy model, and the three experts with the highest matching degree are selected to evaluate the uploaded learning outcomes. The maximum entropy model is described as follows: Assume that the set of models that satisfy all constraints is: The conditional entropy defined on the conditional probability distribution P(Y|X) is: Then the model with the largest conditional entropy H(P) in the model set C is called the maximum entropy model; Learning achievement credit exchange system: including learning achievement levels, credit exchange principles and conversion relationships; the conversion adopts a standardized form, the formula is: Value=V Now -V Min V Max -V Min Value refers to the standardized credit value, V now Refers to the original credit value, V min is the minimum value of this type of learning outcome, and Vmax is the maximum value of this type of learning outcome; Credit recognition for learning outcomes: Experts will recognize the credits of the uploaded outcomes based on the credit exchange system. Each outcome is determined by averaging the credits given by three experts.

5. The credit exchange and consensus building method for inclusive learning outcomes in a credit bank according to claim 1 is further characterized by: The method also includes a consensus building method: Credits are released on the chain: After the experts complete the credit assessment, the system uploads it to the blockchain, and the credits are released on the chain after background review; Consensus of results: Enterprises and users on the blockchain reach a consensus on the previous credit exchange results; Feedback on outcomes: Complete consensus on inclusive learning outcomes for the credit bank and provide feedback.

6. A credit exchange and consensus building system for inclusive learning outcomes in a credit bank, characterized by: It includes an inclusive learning achievement chain request module, a digital label module and an inclusive learning achievement credit exchange module. The inclusive learning achievement chain request module is used to collect inclusive learning achievements and upload them to the blockchain; the digital label module assigns a digital label to each learning achievement, and the digital label includes a digital label for academic education certificates, a digital label for professional qualification certificates, a digital label for social evaluation certificates and a digital label for expert information; the inclusive learning achievement credit exchange module realizes credit conversion and mutual recognition between different learning achievements by screening evaluation experts based on the maximum entropy model.

7. According to claim 6, a credit exchange and consensus building method system for inclusive learning outcomes of credit banks, the inclusive learning outcomes on-chain request module includes three modules: learning outcomes pre-processing, on-chain request and on-chain response: Pre-processing module for inclusive learning outcomes; This includes processing the images and descriptions of three types of achievements: academic education certificates, professional qualification certificates, and social training certificates, and generating personal private keys before uploading to the chain; The module for requesting the uploading of inclusive learning results to the blockchain; upload the learning results images and explanatory text encrypted by the personal private key, and issue a request for uploading the learning results to the blockchain; the system determines whether the accuracy rate is greater than the threshold. When the accuracy rate is less than the threshold, the request for uploading the learning results to the blockchain is rejected as an error message, and when the accuracy rate is greater than or equal to the threshold, the request is uploaded to the blockchain to obtain the block information; The server receives the request module for uploading learning results to the chain, decrypts and verifies it, and gives a response of whether the verification is passed or not.

8. According to claim 7, a credit exchange and consensus building system for inclusive learning outcomes of credit banks, the digital label module comprises: There are four sub-modules: digital labels for academic education certificates, digital labels for professional qualification certificates, digital labels for social evaluation certificates, and digital labels for expert information. Among them: Digital labeling module for academic education certificates: Based on the uploaded academic education pictures and description texts, words are extracted from them to form digital labels for academic education certificates, including school name, academic level, major, and graduation year; Professional qualification certificate digital label module: based on the uploaded professional qualification pictures and description text, extract words from them to form the professional qualification certificate digital label, including certificate name, issuing department, and issuing date; Social evaluation certificate digital label module: based on the uploaded social evaluation certificate pictures and description texts, extract words from them to form the digital label of the social evaluation certificate, including the issuing department and certificate category; Expert information digital labeling module: Based on the expert’s self-introduction text, words are extracted from it to form digital labels for expert information, including the fields of artificial intelligence, education, transportation and logistics, finance, and medical health.

9. According to claim 7, a credit exchange and consensus building system for inclusive learning outcomes of credit banks, the inclusive learning outcomes credit exchange module comprises: The three modules are evaluation expert selection based on the maximum entropy model, learning achievement credit exchange system, and learning achievement credit recognition, among which: Evaluation expert screening module based on maximum entropy model: the text of the evaluation expert and the text of the learning outcome description are matched through the maximum entropy model, and the three experts with the highest matching degree are selected to evaluate the uploaded learning outcomes. The maximum entropy model is described as follows: Assume that the set of models that satisfy all constraints is: The conditional entropy defined on the conditional probability distribution P(Y|X) is: Then the model with the largest conditional entropy H(P) in the model set C is called the maximum entropy model; Learning achievement credit exchange system module: including learning achievement levels, credit exchange principles and conversion relationships; the conversion adopts a standardized form, the formula is: Value refers to the standardized credit value, V now Refers to the original credit value, V min is the minimum value of this type of learning outcome, and Vmax is the maximum value of this type of learning outcome; Learning outcome credit recognition module: Experts certify the credits of uploaded outcomes based on the credit exchange system. Each outcome is determined by averaging the credits given by three experts.

10. According to claim 6, a credit exchange and consensus building system for inclusive learning outcomes of credit banks, the system further comprises a consensus building module, the consensus building module comprises: Credits on-chain publishing module: After the experts complete the credit assessment, the system uploads it to the blockchain, and the credits are published on-chain after background review; Consensus module of results: enterprises and users on the blockchain reach a consensus on the previous credit exchange results; Outcomes Feedback Module: Complete consensus on inclusive learning outcomes for the credit bank and provide feedback.

Images